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

    Neuronpedia

    INDEX
    Explanations

    cannot / will not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PARATOR
    0.88
    ся
    0.85
    ُ
    0.84
    Си
    0.83
    сть
    0.82
    ోతి
    0.80
    Pooled
    0.80
    িং
    0.80
    お待ち
    0.80
    ἷ
    0.80
    POSITIVE LOGITS
    '
    1.16
    将于
    0.95
     at
    0.93
     with
    0.91
    y
    0.91
    መሳሳይ
    0.91
    yards
    0.90
     in
    0.88
    有没有
    0.88
     Website
    0.87
    Act Density 0.223%

    No Known Activations