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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    дина
    -0.06
     gentleman
    -0.06
    ющих
    -0.06
    _CAMERA
    -0.06
     enraged
    -0.06
    Operand
    -0.06
    ADOS
    -0.06
     Catalonia
    -0.06
    ADA
    -0.06
    ulated
    -0.06
    POSITIVE LOGITS
     shorten
    0.06
    .utils
    0.06
     sexist
    0.06
    awaiter
    0.06
     जन
    0.06
     Clears
    0.06
     multit
    0.06
     αποτε
    0.06
    /rc
    0.06
     produk
    0.06
    Act Density 0.027%

    No Known Activations