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

    Neuronpedia

    INDEX
    Explanations

    quoting, emphasis, citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಮತ್ತು
    0.43
     dearly
    0.41
    ಜ
    0.41
     ಸು
    0.41
    Semitic
    0.40
     Stiftung
    0.39
    definite
    0.39
     மற்றும்
    0.39
     ਅਤੇ
    0.39
    arashtra
    0.38
    POSITIVE LOGITS
    引号
    0.55
     emphasis
    0.48
    Zitat
    0.46
     italics
    0.43
    emphasis
    0.42
     강조
    0.42
    这句话
    0.41
    Emphasis
    0.40
     Emphasis
    0.40
     quoting
    0.39
    Act Density 0.003%

    No Known Activations