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

    Neuronpedia

    INDEX
    Explanations

    `:q` command or vim errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AN
    1.48
    EL
    1.33
    RE
    1.27
    AL
    1.23
    ’
    1.23
    أ
    1.23
    EN
    1.10
    ED
    1.10
    ER
    1.09
    IL
    1.09
    POSITIVE LOGITS
    ti
    0.92
    w
    0.92
    meye
    0.86
    representative
    0.80
    ли
    0.79
    cj
    0.79
     hutan
    0.79
    ווי
    0.79
    wem
    0.78
    lll
    0.78
    Act Density 0.000%

    No Known Activations