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

    Neuronpedia

    INDEX
    Explanations

    link

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    區
    -0.07
    Helpers
    -0.07
    .“
    -0.07
    necessary
    -0.06
    ültür
    -0.06
    เล
    -0.06
    [n
    -0.06
    نویس
    -0.06
    Countries
    -0.06
    _bl
    -0.06
    POSITIVE LOGITS
     требования
    0.07
     sido
    0.06
     occas
    0.06
     ваг
    0.06
     verificar
    0.06
    ísticas
    0.06
     Ma
    0.06
     IK
    0.06
     Afghan
    0.05
     ANT
    0.05
    Act Density 0.016%

    No Known Activations