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

    Neuronpedia

    INDEX
    Explanations

    would you like me to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clearly
    0.83
     somewhat
    0.77
     vividly
    0.76
    LinkId
    0.76
     effectively
    0.70
    สุด
    0.68
     tamp
    0.68
    clearly
    0.67
     Somewhat
    0.67
     perfectly
    0.67
    POSITIVE LOGITS
    拣
    0.74
     countenance
    0.73
     hipótes
    0.70
    望
    0.70
    Sorting
    0.68
     અર
    0.68
     ocur
    0.67
    ейчас
    0.66
     fanciful
    0.65
    解码
    0.65
    Act Density 0.236%

    No Known Activations