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

    Neuronpedia

    INDEX
    Explanations

    notes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وفير
    -0.08
     അഭ
    -0.08
     Pakistani
    -0.08
     रोग
    -0.08
     appell
    -0.08
     QColor
    -0.08
     spectaculaire
    -0.07
     limb
    -0.07
     साब
    -0.07
     bathing
    -0.07
    POSITIVE LOGITS
     jot
    0.13
     Notes
    0.10
    碎
    0.09
     notes
    0.09
    Notes
    0.09
     accumulated
    0.09
     작성
    0.08
     accrued
    0.08
    记录
    0.08
     запись
    0.08
    Act Density 0.031%

    No Known Activations