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

    Neuronpedia

    INDEX
    Explanations

    numbers, editions, awards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     každé
    -0.07
     Regional
    -0.06
    aphrag
    -0.06
    랜
    -0.06
    Positive
    -0.06
    Regional
    -0.06
    .Mockito
    -0.06
    cascade
    -0.06
    moved
    -0.06
     Cav
    -0.06
    POSITIVE LOGITS
    :.
    0.07
    ид
    0.07
    ondere
    0.07
    ضافة
    0.07
     :\
    0.07
    ::.
    0.06
    ’ı
    0.06
    ecd
    0.06
    paces
    0.06
    шла
    0.06
    Act Density 0.011%

    No Known Activations