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

    Neuronpedia

    INDEX
    Explanations

    references to spreading information or messages

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

    spread the word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.62
    DockStyle
    -0.57
    lgari
    -0.50
     Roskov
    -0.45
    AddHtmlAttribute
    -0.43
     compromising
    -0.43
    FormTagHelper
    -0.43
    featureID
    -0.42
    緻
    -0.42
    protoimpl
    -0.42
    POSITIVE LOGITS
     spread
    0.59
    Spread
    0.59
    spread
    0.54
     spreads
    0.52
     Spread
    0.51
    tagHelperRunner
    0.44
     difusión
    0.43
     seragam
    0.43
     Signalez
    0.41
     verbreitet
    0.41
    Act Density 0.009%

    No Known Activations