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

    Neuronpedia

    INDEX
    Explanations

    late decades or centuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ྀ
    -0.94
     BOTH
    -0.93
    ſi
    -0.91
     lää
    -0.88
    HER
    -0.88
    entemente
    -0.88
     mères
    -0.88
    uurs
    -0.88
    THING
    -0.85
    OND
    -0.84
    POSITIVE LOGITS
     into
    1.05
     quando
    0.97
     /
    0.94
     to
    0.89
     period
    0.85
     anderen
    0.84
     after
    0.83
    ítez
    0.83
     when
    0.82
    躁
    0.82
    Act Density 0.029%

    No Known Activations