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

    Neuronpedia

    INDEX
    Explanations

    technical processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .car
    -0.07
    เพ
    -0.06
    _ctl
    -0.06
    iph
    -0.06
     peppers
    -0.06
     roulette
    -0.06
     sophomore
    -0.06
    距離
    -0.06
    ppard
    -0.06
     Campbell
    -0.06
    POSITIVE LOGITS
    ulaire
    0.07
     procedural
    0.07
     Якщо
    0.07
     invention
    0.07
     네이트
    0.06
    法院
    0.06
     mevcut
    0.06
     );
↵
    0.06
    Ř
    0.06
    vailability
    0.06
    Act Density 0.283%

    No Known Activations