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

    Neuronpedia

    INDEX
    Explanations

    organizations and institutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aaaaaaaa
    -0.07
    득
    -0.07
     key
    -0.06
    ��
    -0.06
    ogn
    -0.06
    .slide
    -0.06
     seven
    -0.06
    tır
    -0.06
     Arch
    -0.06
    амет
    -0.06
    POSITIVE LOGITS
     Tanzania
    0.07
    —we
    0.06
    pla
    0.06
    .just
    0.06
     Classroom
    0.06
     SolidColorBrush
    0.06
     continues
    0.06
     réuss
    0.06
    _crossentropy
    0.06
     Beatles
    0.06
    Act Density 0.026%

    No Known Activations