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

    Neuronpedia

    INDEX
    Explanations

    Non-English phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     airplanes
    -0.08
    I
    -0.07
     Cold
    -0.07
     Terrorism
    -0.07
     Victory
    -0.07
    ProgressDialog
    -0.06
     aged
    -0.06
    ização
    -0.06
     pd
    -0.06
    pd
    -0.06
    POSITIVE LOGITS
     Elis
    0.06
    _hist
    0.06
     ukon
    0.06
    تين
    0.06
    悟
    0.06
    rowth
    0.06
     حسین
    0.06
    (rgb
    0.06
    %;
↵
    0.05
    -trigger
    0.05
    Act Density 0.055%

    No Known Activations