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

    Neuronpedia

    INDEX
    Explanations

    McDonald's for BULKING

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.36
     و
    0.35
    そして
    0.34
    AND
    0.32
     ۽
    0.31
     &
    0.30
     và
    0.30
     અને
    0.29
     และ
    0.29
     AND
    0.29
    POSITIVE LOGITS
    例如
    0.39
     например
    0.38
    например
    0.38
    比如说
    0.36
     специфи
    0.36
    ຢູ່ໃນ
    0.36
     मसलन
    0.35
     เช่น
    0.35
     tertentu
    0.34
    যেমন
    0.34
    Act Density 0.000%

    No Known Activations