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

    Neuronpedia

    INDEX
    Explanations

    measurement units within parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mici
    0.48
    germeister
    0.46
     mencegah
    0.45
     Monastery
    0.44
     polymerization
    0.44
     isopropyl
    0.44
     porcelain
    0.44
     pois
    0.44
     Lebensmittel
    0.44
     tapi
    0.43
    POSITIVE LOGITS
    response
    0.54
    Ч
    0.48
    АН
    0.48
     питань
    0.48
    feedback
    0.47
    Bloomberg
    0.46
    Ж
    0.46
    非
    0.46
    ΩΝ
    0.46
    ONE
    0.44
    Act Density 0.002%

    No Known Activations