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

    Neuronpedia

    INDEX
    Explanations

    Mixed languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    foon
    -0.07
    逃脱
    -0.07
    (typ
    -0.07
    	FILE
    -0.07
    	atomic
    -0.07
    .surname
    -0.07
    ʐ
    -0.06
    收費
    -0.06
     mutableListOf
    -0.06
     disillusion
    -0.06
    POSITIVE LOGITS
     подпис
    0.08
     cổ
    0.07
    رن
    0.07
     animal
    0.07
    ula
    0.06
    ols
    0.06
    _bottom
    0.06
    郡
    0.06
     PLA
    0.06
    da
    0.06
    Act Density 0.000%

    No Known Activations