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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    派驻
    -0.08
    dorf
    -0.07
     Hof
    -0.07
    cec
    -0.07
    Spider
    -0.07
    itra
    -0.07
    Emma
    -0.06
    surname
    -0.06
    groupBox
    -0.06
    弹性
    -0.06
    POSITIVE LOGITS
     Ay
    0.07
    .convert
    0.07
    調
    0.06
    	hash
    0.06
     negligible
    0.06
    すごい
    0.06
    ܈
    0.06
     תוכנ
    0.06
    _measure
    0.06
     nguồn
    0.06
    Act Density 0.002%

    No Known Activations