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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     基
    -0.07
    ентами
    -0.07
    љ
    -0.07
    率
    -0.06
     Specialty
    -0.06
    adients
    -0.06
     sexkontakte
    -0.06
     元
    -0.06
    .readline
    -0.06
    .Geometry
    -0.06
    POSITIVE LOGITS
    iper
    0.08
    _ANGLE
    0.07
    Perm
    0.07
    -angle
    0.07
    _grade
    0.07
    bac
    0.07
     depois
    0.06
     sulfur
    0.06
    ker
    0.06
    _notifier
    0.06
    Act Density 0.037%

    No Known Activations