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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical values or data representation in text

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

    File paths and URLs

    np_acts-logits-general · gemini-2.0-flash

    code paths and common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MenuView
    -0.71
    SaveChangesAsync
    -0.63
    DockStyle
    -0.62
    ContentAlignment
    -0.58
    DeleteBehavior
    -0.57
     fuite
    -0.57
     unknownFields
    -0.56
    setVerticalGroup
    -0.54
     addSubview
    -0.54
    zzlement
    -0.53
    POSITIVE LOGITS
    common
    0.75
     commons
    0.63
    {}/
    0.63
    core
    0.62
     Common
    0.59
    исленность
    0.59
    httphttps
    0.59
     "..\..\
    0.58
     common
    0.57
    commons
    0.57
    Act Density 0.100%

    No Known Activations