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

    Neuronpedia

    INDEX
    Explanations

    Find links and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dailySales
    1.42
    rvGroup
    1.40
    <unused1098>
    1.38
     resultArray
    1.33
    <unused2132>
    1.30
     modalCard
    1.29
    <unused466>
    1.28
     renderEncoder
    1.28
    रिमेंट
    1.27
    <unused1092>
    1.27
    POSITIVE LOGITS
    0.78
     st
    0.77
    :
    0.75
     almost
    0.74
    -
    0.73
    '
    0.72
    無
    0.72
    on
    0.68
    iz
    0.67
     not
    0.65
    Act Density 0.053%

    No Known Activations