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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    千
    -0.08
     Network
    -0.07
    的品牌
    -0.07
     chiến
    -0.07
     عملية
    -0.07
    ﲤ
    -0.07
     murderous
    -0.06
    移动
    -0.06
     сов
    -0.06
     toolbox
    -0.06
    POSITIVE LOGITS
    EGIN
    0.07
     CLEAR
    0.07
    dration
    0.07
    iaz
    0.07
    곘
    0.07
     told
    0.07
     ambiance
    0.07
    NOTE
    0.07
    Carol
    0.06
    cret
    0.06
    Act Density 0.092%

    No Known Activations