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

    Neuronpedia

    INDEX
    Explanations

    iv

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fran
    -0.06
     уж
    -0.06
    /count
    -0.06
    _using
    -0.06
    (isinstance
    -0.06
    安
    -0.06
    (Account
    -0.06
     मद
    -0.06
    ือข
    -0.06
    (history
    -0.06
    POSITIVE LOGITS
    .Surface
    0.07
    ínu
    0.07
     schem
    0.07
     Simulator
    0.07
     inflater
    0.06
     sind
    0.06
     sistem
    0.06
     trưng
    0.06
     Derm
    0.06
     Incident
    0.06
    Act Density 0.002%

    No Known Activations