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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and conditions involving comparisons and logical operators

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

    biggest/smallest value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.65
    ſſung
    -0.64
    featureID
    -0.61
     Wicidata
    -0.61
    ꊥ
    -0.60
    𑄥
    -0.59
    ꎬ
    -0.59
    WEBPACK
    -0.59
    <pad>
    -0.58
    [@BOS@]
    -0.58
    POSITIVE LOGITS
     naturels
    0.41
    routeProvider
    0.39
     šķ
    0.33
    nyataan
    0.32
    ्ड
    0.30
     mauvaise
    0.29
     ordinaires
    0.29
     between
    0.29
     migrantes
    0.28
    vénients
    0.28
    Act Density 0.010%

    No Known Activations