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

    Neuronpedia

    INDEX
    Explanations

    quantitative data, particularly numerical values and their magnitudes

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

    The number "2"

    np_acts-logits-general · gemini-2.0-flash

    the digit 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.66
    存于互联网档案馆
    -0.62
     Ston
    -0.51
     seren
    -0.50
    drawiam
    -0.49
    ?''
    -0.48
    ”]
    -0.48
    ASHI
    -0.48
     beant
    -0.48
    UAGE
    -0.48
    POSITIVE LOGITS
    IonicModule
    0.59
    tagHelperRunner
    0.59
    );
    0.57
    aarrggbb
    0.55
     surla
    0.54
    GraphicsUnit
    0.54
    цездатний
    0.53
    ftagPool
    0.53
     createState
    0.52
    stddef
    0.52
    Act Density 1.997%

    No Known Activations