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

    Neuronpedia

    INDEX
    Explanations

    single quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    طال
    -0.07
    句话
    -0.07
    และ
    -0.07
     replaced
    -0.07
    ώρα
    -0.07
    ír
    -0.07
     impecc
    -0.07
    ुल
    -0.06
     cramped
    -0.06
    bulk
    -0.06
    POSITIVE LOGITS
     ‘
    0.11
     '
    0.10
    ‘
    0.07
     "'
    0.07
    ニﾆ
    0.07
    'I
    0.07
     cocktails
    0.07
    "'
    0.06
     Ary
    0.06
     ’
    0.06
    Act Density 0.031%

    No Known Activations