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

    Neuronpedia

    INDEX
    Explanations

    instances of explanation and instruction within a technical context

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

    combining to deliver results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.41
    AddTagHelper
    -0.37
     myſelf
    -0.36
     llorar
    -0.34
     remplacer
    -0.34
    長の
    -0.33
    unteer
    -0.32
     selatan
    -0.31
    __*/
    -0.30
    :][
    -0.30
    POSITIVE LOGITS
    DockStyle
    0.75
     NSCoder
    0.60
    BeginContext
    0.57
     synerg
    0.56
    protoimpl
    0.55
     crossorigin
    0.52
     synergistic
    0.52
    Personendaten
    0.51
     Combo
    0.50
     combination
    0.50
    Act Density 0.236%

    No Known Activations