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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Security
    -0.08
    hapus
    -0.08
    _Vector
    -0.07
    _without
    -0.07
     yaptı
    -0.07
    注销
    -0.07
    椸
    -0.07
    thèse
    -0.07
    _payment
    -0.07
     الز
    -0.07
    POSITIVE LOGITS
    라도
    0.07
    ⑅
    0.07
     deal
    0.06
    تان
    0.06
     Sophia
    0.06
    (pp
    0.06
    iler
    0.06
     lad
    0.06
    iloc
    0.06
     differ
    0.06
    Act Density 0.017%

    No Known Activations