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

    Neuronpedia

    INDEX
    Explanations

    yl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appear
    -0.07
    -modal
    -0.07
    感触
    -0.07
     Theft
    -0.07
     Bit
    -0.07
    تكوين
    -0.06
     HTTP
    -0.06
     Generation
    -0.06
    -making
    -0.06
    node
    -0.06
    POSITIVE LOGITS
    扩大
    0.07
     urged
    0.07
    ----------------------------
    0.06
    enti
    0.06
    ıldı
    0.06
    staticmethod
    0.06
    𝙤
    0.06
    찼
    0.06
    direct
    0.06
    circ
    0.06
    Act Density 0.017%

    No Known Activations