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

    Neuronpedia

    INDEX
    Explanations

    at the very end of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Şubat
    1.14
     ľ
    1.12
     incline
    1.10
     Agustus
    1.10
     Sosial
    1.06
     imposs
    1.05
     egli
    1.04
     thine
    1.03
    ⸜
    1.03
     Jn
    1.01
    POSITIVE LOGITS
    ef
    1.29
    est
    1.03
    д
    1.02
    ek
    0.98
    에
    0.97
    に
    0.93
    एम
    0.92
    ens
    0.91
    কে
    0.91
    anding
    0.91
    Act Density 0.134%

    No Known Activations