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

    Neuronpedia

    INDEX
    Explanations

    Technical/academic text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    طال
    -0.07
     του
    -0.07
     Зав
    -0.07
    ζό
    -0.07
     소
    -0.06
     Corey
    -0.06
    ivirus
    -0.06
    atic
    -0.06
     force
    -0.06
    γορ
    -0.06
    POSITIVE LOGITS
    expl
    0.07
     acess
    0.06
    한국
    0.06
     мож
    0.06
     OSX
    0.06
     Antarctica
    0.06
    ait
    0.06
     mary
    0.06
    _US
    0.06
     internacional
    0.06
    Act Density 0.481%

    No Known Activations