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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ностью
    -0.07
    Writing
    -0.06
    ’nın
    -0.06
    36
    -0.06
     GO
    -0.06
    olecular
    -0.06
    .Imp
    -0.06
     Ali
    -0.06
    //================================================================
    -0.06
    flush
    -0.06
    POSITIVE LOGITS
     Đại
    0.06
     rasp
    0.06
     advertisements
    0.06
     UFC
    0.06
     jb
    0.06
    .isAdmin
    0.06
     GTK
    0.06
    _experience
    0.06
     좌
    0.06
     Rupert
    0.06
    Act Density 0.027%

    No Known Activations