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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sauna
    -0.07
    .logo
    -0.07
    .epsilon
    -0.07
    _empresa
    -0.06
    _appro
    -0.06
    .modelo
    -0.06
     angry
    -0.06
     condiciones
    -0.06
     domin
    -0.06
     partido
    -0.06
    POSITIVE LOGITS
    };
↵
↵
    0.06
    ニニニニ
    0.06
    arts
    0.06
     USART
    0.06
    ickou
    0.06
     τελευτα
    0.06
     mongoose
    0.06
     TAKE
    0.06
    ：↵↵
    0.06
    antha
    0.06
    Act Density 0.002%

    No Known Activations