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

    Neuronpedia

    INDEX
    Explanations

    Using

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     todavía
    -0.07
    FLOW
    -0.06
    $view
    -0.06
     Dion
    -0.06
    坠
    -0.06
     chill
    -0.06
    {
    -0.06
    .flex
    -0.06
    _foot
    -0.06
    Basket
    -0.06
    POSITIVE LOGITS
     Using
    0.08
     using
    0.08
     محافظ
    0.07
    觋
    0.07
     язык
    0.07
     وه
    0.07
    🍏
    0.07
    משחק
    0.07
    党和国家
    0.07
    方式
    0.07
    Act Density 0.042%

    No Known Activations