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

    Neuronpedia

    INDEX
    Explanations

    breaking down and explaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !,
    1.40
    *,
    1.37
    ,/
    1.36
    /,
    1.36
    ,
    1.33
    **,
    1.31
    ,*
    1.30
    ™,
    1.26
    ，
    1.26
    ;,
    1.26
    POSITIVE LOGITS
    はその
    0.79
    الغ
    0.79
     لم
    0.78
     minden
    0.78
     لا
    0.78
     હ
    0.75
    꽤
    0.73
     گیا۔
    0.73
     ك
    0.71
     પ્ર
    0.71
    Act Density 0.155%

    No Known Activations