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

    Neuronpedia

    INDEX
    Explanations

    ec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arendra
    -0.07
     Maar
    -0.07
     pain
    -0.06
    analy
    -0.06
     mãe
    -0.06
     guerra
    -0.06
     meş
    -0.06
    альному
    -0.06
     kötü
    -0.06
    midt
    -0.06
    POSITIVE LOGITS
     Banco
    0.07
    .baidu
    0.07
    _double
    0.07
     distrib
    0.07
     overtime
    0.06
     CNN
    0.06
     attractive
    0.06
     ///↵
    0.06
     express
    0.06
     ไทย
    0.06
    Act Density 0.000%

    No Known Activations