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

    Neuronpedia

    INDEX
    Explanations

    variable assignment or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %'
    0.74
    嗯
    0.74
    {#
    0.73
    !='
    0.69
    叫做
    0.67
     cetera
    0.66
    =\"
    0.66
    ...”
    0.65
    ＂
    0.63
     tương
    0.63
    POSITIVE LOGITS
     was
    0.75
     =
    0.73
    izada
    0.68
    ovali
    0.66
    naked
    0.66
    <unused1198>
    0.66
     +,
    0.65
     +/-
    0.64
     दट
    0.63
     were
    0.62
    Act Density 0.186%

    No Known Activations