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

    Neuronpedia

    INDEX
    Explanations

    academic articles and information links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    လ်
    0.37
    ulen
    0.36
    莳
    0.35
    äter
    0.35
    針對
    0.34
    無
    0.34
    erunner
    0.34
    南
    0.34
    高品質
    0.33
    适用于
    0.33
    POSITIVE LOGITS
     Beispiele
    0.45
     kuchh
    0.45
     guidebook
    0.42
     FAQs
    0.42
    parte
    0.40
    នៅក្នុង
    0.40
     стр
    0.40
     Wikipedia
    0.40
     wikipedia
    0.40
     पुस्तक
    0.39
    Act Density 0.017%

    No Known Activations