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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upright
    -0.07
     mus
    -0.07
     pledge
    -0.06
     Paul
    -0.06
    Pes
    -0.06
    аніз
    -0.06
     Cove
    -0.06
    ba
    -0.06
     salads
    -0.06
     Seite
    -0.06
    POSITIVE LOGITS
    τύ
    0.07
    align
    0.07
    .userService
    0.06
    .about
    0.06
    _TRANSFORM
    0.06
    ी)
    0.06
    Iterator
    0.06
    لال
    0.06
     incumbent
    0.06
     انتقال
    0.06
    Act Density 0.065%

    No Known Activations