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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sistência
    -0.07
    -su
    -0.07
    鱼类
    -0.07
    itant
    -0.07
    极度
    -0.07
    呵护
    -0.06
     sentenced
    -0.06
    thumbnail
    -0.06
     segmented
    -0.06
    bul
    -0.06
    POSITIVE LOGITS
     Ergebn
    0.07
    燚
    0.07
    ‼
    0.07
    ╘
    0.07
    桁
    0.07
    ⇗
    0.07
    _dead
    0.06
    夺冠
    0.06
     Rows
    0.06
    เฮ
    0.06
    Act Density 0.044%

    No Known Activations