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

    Neuronpedia

    INDEX
    Explanations

    singer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    澹
    -0.07
    תוש
    -0.07
     aValue
    -0.07
     yielded
    -0.07
    박
    -0.07
     hẳ
    -0.06
    美味し
    -0.06
    »,
    -0.06
     four
    -0.06
     evaluate
    -0.06
    POSITIVE LOGITS
     singer
    0.09
     Shift
    0.08
    /she
    0.07
    .commons
    0.07
    耶稣
    0.07
     pomp
    0.07
    _sync
    0.07
     finite
    0.07
    _cnt
    0.07
    指导意见
    0.07
    Act Density 0.007%

    No Known Activations