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

    Neuronpedia

    INDEX
    Explanations

    multiple items or quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    -2.33
    1
    -2.14
    -
    -2.08
    those
    -2.05
    那些
    -1.98
    .
    -1.90
    <
    -1.89
    ^
    -1.80
    Your
    -1.77
    —
    -1.73
    POSITIVE LOGITS
     dozen
    1.95
     armadura
    1.92
    おはよう
    1.88
    棪
    1.88
    黩
    1.88
     și
    1.88
     trän
    1.86
     jsme
    1.83
     näh
    1.83
     parachoque
    1.80
    Act Density 0.059%

    No Known Activations