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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jackets
    -0.07
    熏
    -0.07
     exams
    -0.07
    udging
    -0.07
     Coal
    -0.07
    _Settings
    -0.07
    _NOT
    -0.07
    济宁
    -0.07
    管家
    -0.07
     Volley
    -0.07
    POSITIVE LOGITS
    例
    0.07
     approval
    0.07
    ⇆
    0.06
    ии
    0.06
    '],['
    0.06
     participação
    0.06
    �权
    0.06
     рождения
    0.06
    يرة
    0.06
    tatus
    0.06
    Act Density 0.003%

    No Known Activations