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

    Neuronpedia

    INDEX
    Explanations

    licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    年龄
    -0.07
    |.↵
    -0.07
    ꪜ
    -0.07
    ~,
    -0.06
    无论如何
    -0.06
     types
    -0.06
    看好
    -0.06
     knew
    -0.06
     transferred
    -0.06
     accept
    -0.06
    POSITIVE LOGITS
     lj
    0.07
     lamb
    0.07
    ﺋ
    0.07
    一句
    0.07
    סכום
    0.07
     Quar
    0.07
     userData
    0.07
     fj
    0.07
     Lid
    0.07
    _prec
    0.07
    Act Density 0.053%

    No Known Activations