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

    Neuronpedia

    INDEX
    Explanations

    Diverse concepts and language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Batı
    -0.06
    aclass
    -0.06
     pwd
    -0.06
     nhiễ
    -0.06
    Sexy
    -0.06
     varias
    -0.06
    yeah
    -0.06
    blade
    -0.06
    دهای
    -0.06
    -era
    -0.05
    POSITIVE LOGITS
     clientele
    0.07
     ع
    0.07
    .fin
    0.06
     msgstr
    0.06
     choose
    0.06
     imp
    0.06
     إ
    0.06
    ENDED
    0.06
     InputStreamReader
    0.06
    .inflate
    0.06
    Act Density 0.222%

    No Known Activations