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

    Neuronpedia

    INDEX
    Explanations

    percentages and quantifiable values in the text

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

    Percentage values

    np_acts-logits-general · gemini-2.0-flash

    percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    moveToFirst
    -0.57
    Einzelnachweise
    -0.55
    ;">
    -0.55
    andosi
    -0.53
    curious
    -0.52
    ---*/
    -0.52
     nhàng
    -0.52
    🏾
    -0.52
    organize
    -0.52
     Stein
    -0.52
    POSITIVE LOGITS
     percent
    0.92
     Prozent
    0.85
     \%$
    0.84
    -%
    0.83
    %
    0.78
     (%)
    0.77
    percent
    0.75
    ,%
    0.75
    /%
    0.73
    ؜
    0.72
    Act Density 0.356%

    No Known Activations