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

    Neuronpedia

    INDEX
    Explanations

    still

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    辰
    -0.07
    信
    -0.07
    들을
    -0.07
     guarding
    -0.07
     bonds
    -0.07
     adult
    -0.07
    审核
    -0.06
     seus
    -0.06
    Case
    -0.06
     schools
    -0.06
    POSITIVE LOGITS
     fran
    0.07
    �
    0.07
    刻苦
    0.07
    _enum
    0.07
    各行各业
    0.07
    𝚘
    0.07
     pne
    0.07
     DRIVER
    0.06
    ◕
    0.06
    <TKey
    0.06
    Act Density 0.084%

    No Known Activations