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

    Neuronpedia

    INDEX
    Explanations

    repeating content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fName
    -0.06
    ()})↵
    -0.06
     versions
    -0.06
    _Do
    -0.06
     погод
    -0.06
     '..',
    -0.06
    ��
    -0.06
    ὶ
    -0.06
     σε
    -0.06
     Tiếng
    -0.05
    POSITIVE LOGITS
    眾
    0.07
    oki
    0.06
    Character
    0.06
     Scandinavian
    0.06
     departing
    0.06
    relu
    0.06
    igrated
    0.06
    恩
    0.06
    family
    0.06
    區
    0.06
    Act Density 0.006%

    No Known Activations