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

    Neuronpedia

    INDEX
    Explanations

    backing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    异常
    -0.09
     ssize
    -0.09
    angaje
    -0.08
     paradox
    -0.08
     Recursive
    -0.08
    fang
    -0.07
    锐
    -0.07
     атом
    -0.07
     tượng
    -0.07
     Fahrenheit
    -0.07
    POSITIVE LOGITS
     accompaniment
    0.17
     साथी
    0.11
     backing
    0.11
     begeleiding
    0.11
    Supporting
    0.10
    Backing
    0.10
     accompan
    0.10
     accompagner
    0.10
    伴
    0.10
     accomp
    0.10
    Act Density 0.013%

    No Known Activations