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

    Neuronpedia

    INDEX
    Explanations

    charset/doctype tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Max
    -0.09
    ("");↵
    -0.07
    舒
    -0.07
    ANGER
    -0.07
     $("#
    -0.07
     compliance
    -0.07
    免费
    -0.07
    费率
    -0.07
    吆
    -0.07
    ','$
    -0.07
    POSITIVE LOGITS
     vehicle
    0.07
    istas
    0.07
     aura
    0.07
     raison
    0.07
     handic
    0.07
     счита
    0.07
     iliş
    0.07
    essential
    0.07
     situação
    0.07
     вопрос
    0.07
    Act Density 0.001%

    No Known Activations