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

    Neuronpedia

    INDEX
    Explanations

    study what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    1.88
    ING
    1.49
    AN
    1.43
    在
    1.43
    ;
    1.42
    AL
    1.40
    EN
    1.36
    '
    1.35
    ை
    1.33
    AT
    1.32
    POSITIVE LOGITS
    다면
    1.23
    م
    1.18
    اب
    1.16
    다
    1.05
    ಂದು
    1.04
    تی
    1.00
    ны
    0.98
    ete
    0.98
    elt
    0.97
    ли
    0.96
    Act Density 0.000%

    No Known Activations