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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    לידה
    -0.08
     palms
    -0.08
    ት
    -0.07
     dengan
    -0.07
     dignity
    -0.07
     Yoga
    -0.07
    ictions
    -0.06
     Wellness
    -0.06
    骸
    -0.06
     MEDIA
    -0.06
    POSITIVE LOGITS
     spo
    0.07
    minate
    0.07
    obsolete
    0.07
    俺
    0.07
    自主研发
    0.07
    下一步
    0.07
    _jump
    0.07
    ↵↵
    0.07
    Trace
    0.07
     Emit
    0.07
    Act Density 0.001%

    No Known Activations