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

    Neuronpedia

    INDEX
    Explanations

    zh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Same
    -0.07
    ?a
    -0.07
     provinces
    -0.07
    芦
    -0.06
    ystery
    -0.06
    vac
    -0.06
     accreditation
    -0.06
    éné
    -0.06
    Mov
    -0.06
    _dc
    -0.06
    POSITIVE LOGITS
    _classes
    0.08
     zurück
    0.08
     GitHub
    0.07
     aute
    0.07
    andler
    0.07
    istik
    0.07
    장님
    0.07
     характер
    0.07
    징
    0.07
     konnte
    0.07
    Act Density 0.009%

    No Known Activations