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

    Neuronpedia

    INDEX
    Explanations

    economic and environmental metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     velvety
    0.59
    \
    0.57
    Maximum
    0.54
    :
    0.54
    ؟؟
    0.53
     bietet
    0.52
    CurrentByte
    0.52
     deformable
    0.52
     notepad
    0.51
     the
    0.51
    POSITIVE LOGITS
    誓
    0.53
     στον
    0.52
    érin
    0.51
     and
    0.50
     undertakings
    0.50
    出行
    0.49
     અને
    0.49
     ముఖ్య
    0.48
     نصی
    0.48
    และ
    0.47
    Act Density 0.001%

    No Known Activations