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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values and punctuation in the text

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

    category lists references awards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.81
    httphttps
    -0.79
    ValueStyle
    -0.68
     resourceCulture
    -0.64
     Paglinawan
    -0.63
    WireFormatLite
    -0.60
    AxisAlignment
    -0.57
    awtextra
    -0.55
     autorytatywna
    -0.55
    ">//
    -0.52
    POSITIVE LOGITS
     eşofman
    0.38
     mourut
    0.37
    감
    0.36
    ngOnDestroy
    0.34
    dialement
    0.34
     oyuncak
    0.34
    IfNeeded
    0.34
    droje
    0.33
    бина
    0.33
    .*")]
    0.31
    Act Density 0.038%

    No Known Activations