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

    Neuronpedia

    INDEX
    Explanations

    condensation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    送上
    -0.07
     iteration
    -0.07
    妝
    -0.07
     Crop
    -0.07
     transit
    -0.07
    弹性
    -0.06
    졵
    -0.06
    rett
    -0.06
     bruk
    -0.06
    绵
    -0.06
    POSITIVE LOGITS
    ız
    0.08
    קוד
    0.07
    ◇
    0.07
     filles
    0.07
    conds
    0.07
    _RESULT
    0.07
    的身体
    0.07
     tys
    0.07
    yla
    0.07
     katıl
    0.07
    Act Density 0.003%

    No Known Activations