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

    Neuronpedia

    INDEX
    Explanations

    Pass Rate, Face Value, Downside Deviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    entreprise
    0.80
     sociétés
    0.73
    amacare
    0.71
    ʿ
    0.68
    DCs
    0.66
    ḏ
    0.66
    personas
    0.66
    大規模
    0.66
    ヴィ
    0.64
     república
    0.64
    POSITIVE LOGITS
     coefficient
    0.86
     number
    0.83
     =
    0.82
     coefficients
    0.80
     \
    0.77
     $=
    0.77
     modulus
    0.74
    =
    0.72
     \\
    0.71
    _
    0.71
    Act Density 0.401%

    No Known Activations