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
     อ
    -0.06
    郭
    -0.06
    formance
    -0.06
    ])+
    -0.06
     Bà
    -0.06
     퍼
    -0.06
     cara
    -0.06
     kola
    -0.06
     loose
    -0.06
     Stout
    -0.06
    POSITIVE LOGITS
     int
    0.07
     semana
    0.07
     '*'
    0.06
     desert
    0.06
     Enjoy
    0.06
     확인
    0.06
     upset
    0.06
    �
    0.06
     beaches
    0.06
     humanity
    0.06
    Act Density 0.000%

    No Known Activations