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

    Neuronpedia

    INDEX
    Explanations

    job application responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Administrator
    -0.08
    身亡
    -0.06
     signup
    -0.06
    外婆
    -0.06
     Stra
    -0.06
    化石
    -0.06
     Un
    -0.06
     Mang
    -0.06
    方方面面
    -0.06
     entrepreneur
    -0.06
    POSITIVE LOGITS
    베
    0.07
     remaining
    0.07
    łoży
    0.07
     jams
    0.07
    odata
    0.07
    壬
    0.06
    ôm
    0.06
    ᅵ
    0.06
    ~":"
    0.06
     nah
    0.06
    Act Density 0.010%

    No Known Activations