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

    Neuronpedia

    INDEX
    Explanations

    paralysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Omar
    -0.08
     landscaping
    -0.08
     işlem
    -0.08
     பாட
    -0.08
     knew
    -0.07
    omas
    -0.07
    ogy
    -0.07
    xo
    -0.07
     OG
    -0.07
     OD
    -0.07
    POSITIVE LOGITS
    /we
    0.08
     детей
    0.08
     клиентов
    0.08
    weights
    0.08
     guidance
    0.07
     кишеч
    0.07
    เครื่อง
    0.07
     vítimas
    0.07
     живота
    0.07
     неправиль
    0.07
    Act Density 0.005%

    No Known Activations