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

    Neuronpedia

    INDEX
    Explanations

    then again or on the other hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     julho
    0.72
     especies
    0.72
     arquivo
    0.71
    獼
    0.67
    위원회
    0.66
    }^{*}$,
    0.64
     дзяржа
    0.63
    類型
    0.63
     archivo
    0.63
    相當
    0.63
    POSITIVE LOGITS
     I
    1.09
    I
    0.93
    t
    0.92
    B
    0.91
     $
    0.89
    L
    0.86
    R
    0.86
     was
    0.85
    X
    0.85
    N
    0.81
    Act Density 0.000%

    No Known Activations