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

    Neuronpedia

    INDEX
    Explanations

    software modification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    llx
    -0.08
    modes
    -0.07
    -year
    -0.07
     requesting
    -0.07
     staples
    -0.07
     regexp
    -0.06
     undergraduate
    -0.06
    maid
    -0.06
     Alto
    -0.06
    .def
    -0.06
    POSITIVE LOGITS
    �
    0.07
     чор
    0.06
     womens
    0.06
     sare
    0.06
    UNITY
    0.06
    _CODES
    0.06
    ERN
    0.06
    �
    0.06
     biç
    0.06
    Erro
    0.06
    Act Density 0.172%

    No Known Activations