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

    Neuronpedia

    INDEX
    Explanations

    pseudocode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.84
     a
    1.50
    h
    1.20
    ان
    1.19
    es
    1.10
    ara
    1.10
    া
    1.09
    ay
    1.08
    ain
    1.08
    et
    1.06
    POSITIVE LOGITS
    ка
    1.14
    т
    1.04
    ك
    1.03
     pseud
    0.86
     pseudo
    0.85
    지의
    0.85
     tenements
    0.84
    지
    0.81
     rostro
    0.79
     Pseudo
    0.79
    Act Density 0.003%

    No Known Activations