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

    Neuronpedia

    INDEX
    Explanations

    occurrences of object instantiation and assignments in code snippets

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

    Code or configuration snippets

    np_acts-logits-general · gemini-2.0-flash

    new object initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ‘
    -0.72
     '
    -0.68
    +'.
    -0.65
    ModelAdmin
    -0.64
     '@
    -0.64
     '$
    -0.64
    -'
    -0.63
    featureID
    -0.62
     '-
    -0.61
     StringTokenizer
    -0.60
    POSITIVE LOGITS
    null
    1.02
     null
    0.92
     new
    0.79
    new
    0.72
    Null
    0.57
     create
    0.55
    create
    0.55
    init
    0.51
    ագրություններ
    0.50
    новништво
    0.48
    Act Density 0.077%

    No Known Activations