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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("!
    -0.07
    _errors
    -0.07
     exclus
    -0.07
     szczeg
    -0.07
    lessons
    -0.07
    (sort
    -0.07
    Ѐ
    -0.07
    慆
    -0.06
    arsimp
    -0.06
    essor
    -0.06
    POSITIVE LOGITS
    MC
    0.07
     EURO
    0.07
    _image
    0.07
    CM
    0.07
     Según
    0.07
     Keeping
    0.07
    见过
    0.07
    有效的
    0.07
    ViewModel
    0.06
    .Trim
    0.06
    Act Density 0.029%

    No Known Activations