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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لازم
    -0.07
    "label
    -0.07
     bv
    -0.07
     Collection
    -0.07
     makeStyles
    -0.07
    🎵
    -0.07
    -designed
    -0.07
     evidently
    -0.07
     tunes
    -0.07
     finely
    -0.07
    POSITIVE LOGITS
     removes
    0.07
     эфф
    0.07
    建議
    0.06
    亚
    0.06
    듷
    0.06
    تر
    0.06
     interrupted
    0.06
    '↵↵↵↵
    0.06
    amer
    0.06
     bik
    0.06
    Act Density 0.013%

    No Known Activations