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

    Neuronpedia

    INDEX
    Explanations

    Nebraska, Service, Clio, Frustration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    특별시
    1.07
    יות
    0.93
    ação
    0.80
    taining
    0.80
    tedir
    0.79
    ierten
    0.79
    客様
    0.77
    methyl
    0.77
    ことなく
    0.77
    lere
    0.75
    POSITIVE LOGITS
    ar
    1.16
    at
    1.11
    as
    1.08
    ور
    1.04
    ang
    1.02
    an
    0.99
    us
    0.96
    ing
    0.89
    ag
    0.88
    in
    0.84
    Act Density 0.509%

    No Known Activations