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

    Neuronpedia

    INDEX
    Explanations

    improvements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hoa
    -0.07
     میان
    -0.06
     SAS
    -0.06
     ngay
    -0.06
    util
    -0.06
    RDD
    -0.06
     kako
    -0.06
     amalg
    -0.06
    _increase
    -0.06
     Hakk
    -0.06
    POSITIVE LOGITS
    σφ
    0.06
    цин
    0.06
     textBox
    0.06
    ecessarily
    0.06
     прох
    0.06
    eln
    0.06
    oten
    0.06
     соці
    0.06
    .output
    0.06
    facebook
    0.06
    Act Density 0.053%

    No Known Activations