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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /x
    -0.08
    家族
    -0.07
    cedes
    -0.07
     الفت
    -0.07
     PropertyInfo
    -0.07
    ercicio
    -0.07
     Nach
    -0.07
     Administrative
    -0.07
    ា
    -0.07
     olduğ
    -0.07
    POSITIVE LOGITS
    Measured
    0.07
     Put
    0.07
    .disable
    0.06
    -connect
    0.06
    END
    0.06
    las
    0.06
    -push
    0.06
     hod
    0.06
    �
    0.06
    فرنس
    0.06
    Act Density 0.147%

    No Known Activations