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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ctrl
    -0.07
    578
    -0.07
     Dön
    -0.06
    Foo
    -0.06
     OCI
    -0.06
    _books
    -0.06
     Méd
    -0.06
    atıcı
    -0.06
    Naz
    -0.06
    abcdefgh
    -0.06
    POSITIVE LOGITS
    ط
    0.07
    yling
    0.07
    닝
    0.07
     ход
    0.07
    ulates
    0.07
    otherapy
    0.06
     treatments
    0.06
     Physiology
    0.06
    .localtime
    0.06
     tất
    0.06
    Act Density 0.010%

    No Known Activations