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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     educ
    -0.07
     ری
    -0.06
     adulthood
    -0.06
    ائ
    -0.06
     батьків
    -0.06
     freelance
    -0.06
    _resources
    -0.06
    tanggal
    -0.06
     клуб
    -0.06
     văn
    -0.06
    POSITIVE LOGITS
     factors
    0.06
    .onChange
    0.06
    اغ
    0.06
    {(
    0.06
    ‌کنندگان
    0.06
    852
    0.06
     quotient
    0.06
    μορ
    0.06
    �
    0.06
    تاب
    0.06
    Act Density 0.018%

    No Known Activations