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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    complete
    -0.08
    ђ
    -0.07
    quoise
    -0.07
    把自己的
    -0.07
    wj
    -0.07
     viet
    -0.07
     ka
    -0.07
     composing
    -0.07
     bring
    -0.07
    _both
    -0.07
    POSITIVE LOGITS
     >
    0.07
    违法犯罪
    0.07
    \Data
    0.07
     findings
    0.07
    钓鱼
    0.06
    創業
    0.06
    xAE
    0.06
    越大
    0.06
     Arrow
    0.06
     diarrhea
    0.06
    Act Density 0.037%

    No Known Activations