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

    Neuronpedia

    INDEX
    Explanations

    class constructors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =
    0.63
    ation
    0.61
    ة
    0.60
    \
    0.59
    (=
    0.59
    Also
    0.58
    Щ
    0.58
    +
    0.57
    However
    0.55
    /
    0.53
    POSITIVE LOGITS
     ctx
    0.84
    params
    0.80
     params
    0.79
     frm
    0.79
    ㎠
    0.77
     вид
    0.77
     codigo
    0.74
    ീകരണ
    0.74
    alertDialog
    0.73
    𒅗
    0.72
    Act Density 0.759%

    No Known Activations