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

    Neuronpedia

    INDEX
    Explanations

    cells

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    غل
    -0.06
     medieval
    -0.06
     key
    -0.06
    idge
    -0.06
     arbitrary
    -0.06
    -0.06
     mariage
    -0.06
     ilç
    -0.06
     CNBC
    -0.06
     compass
    -0.06
    POSITIVE LOGITS
    ров
    0.06
     міста
    0.06
    [user
    0.06
    (validate
    0.06
     remove
    0.06
    rvé
    0.06
    がない
    0.06
    ちょ
    0.05
    Сп
    0.05
    comments
    0.05
    Act Density 0.008%

    No Known Activations