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

    Neuronpedia

    INDEX
    Explanations

    the term "Search."

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

    Code, errors, or descriptions

    np_acts-logits-general · gemini-2.0-flash

    citizen of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.76
    ArrowToggle
    -0.66
    IndentedString
    -0.61
    setVerticalGroup
    -0.59
     communiquez
    -0.59
    adpleegd
    -0.58
    elemField
    -0.56
    toMatchSnapshot
    -0.56
    WidgetItem
    -0.56
    UnsafeEnabled
    -0.55
    POSITIVE LOGITS
     CCL
    0.61
     ſmall
    0.57
     pleaſure
    0.55
     IRIS
    0.54
     Diſ
    0.51
     ſche
    0.51
     SNCF
    0.50
     inscription
    0.49
     Trink
    0.49
     tartalomajánló
    0.48
    Act Density 0.089%

    No Known Activations