Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "More" indicating additional content or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows the word "More" and indicates specificity

    np_acts-logits-general · gemini-2.0-flash

    more followed by specificity or detail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NgModule
    -0.85
    SourceChecksum
    -0.83
    Geplaatst
    -0.79
    ftagPool
    -0.78
    __()
    -0.67
    featureID
    -0.66
    MockBean
    -0.61
     AssemblyCulture
    -0.61
    IContainer
    -0.60
    AndEndTag
    -0.60
    POSITIVE LOGITS
     specifically
    0.66
    Specifically
    0.62
     Specifically
    0.61
     Audiodateien
    0.57
     particuli
    0.55
     Details
    0.54
     importantly
    0.54
     específicamente
    0.52
     good
    0.52
     precisely
    0.51
    Act Density 0.116%

    No Known Activations