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

    Neuronpedia

    INDEX
    Explanations

    percentage values and related statistical terms

    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
     fla
    -0.58
    GGLE
    -0.57
    las
    -0.54
     rocas
    -0.53
    andosi
    -0.52
    fang
    -0.51
    Einzelnachweise
    -0.51
    fla
    -0.50
    oust
    -0.49
    SETTINGS
    -0.49
    POSITIVE LOGITS
     \%$
    1.06
    }%
    1.04
     percent
    0.93
    \%
    0.91
    -%
    0.90
    ؜
    0.90
     (%)
    0.89
     (\%)
    0.88
    $\%
    0.86
    percent
    0.86
    Act Density 0.238%

    No Known Activations