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

    Neuronpedia

    INDEX
    Explanations

    quoting or using specific snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ob
    0.46
     treo
    0.46
     கேட்ட
    0.44
     एमजी
    0.42
    고요
    0.42
    اوم
    0.42
    刷新
    0.42
    t
    0.42
     withdrawn
    0.41
    شمند
    0.41
    POSITIVE LOGITS
     analyses
    0.55
     authorship
    0.50
    RELATIVA
    0.49
    弈
    0.48
     маши
    0.48
     operandSize
    0.48
     Analyses
    0.46
    芷
    0.45
     analisi
    0.44
     tastes
    0.44
    Act Density 0.000%

    No Known Activations