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

    Neuronpedia

    INDEX
    Explanations

    Breakdown of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NE
    0.67
     phen
    0.67
     redistributed
    0.67
     REM
    0.63
     ench
    0.63
    mut
    0.62
    THA
    0.62
     principal
    0.61
    дать
    0.61
     tires
    0.61
    POSITIVE LOGITS
     mannit
    0.63
    uerre
    0.59
     mannitol
    0.58
     xgboost
    0.58
    iesi
    0.55
     عكس
    0.54
    vective
    0.54
    域
    0.54
    ক্ষেপ
    0.53
    asambhavam
    0.53
    Act Density 0.159%

    No Known Activations