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

    Neuronpedia

    INDEX
    Explanations

    freedom, some, ml

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mechanical
    0.51
    罨
    0.51
     MECHANICAL
    0.49
    主角
    0.48
     Fractions
    0.47
     Mechan
    0.47
     fracciones
    0.46
     Bacterial
    0.46
     dents
    0.45
     Coefficients
    0.45
    POSITIVE LOGITS
    نا
    0.48
     contend
    0.47
     غير
    0.46
    ad
    0.46
    َيْ
    0.45
     توجه
    0.44
     مي‌
    0.44
     شب
    0.44
     المسي
    0.43
    ká
    0.43
    Act Density 0.000%

    No Known Activations