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

    Neuronpedia

    INDEX
    Explanations

    Iris Dataset, distances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    1.25
    μός
    1.23
     densément
    1.16
     mínimo
    1.15
     slechts
    1.09
    い
    1.09
     있으며
    1.07
     signif
    1.05
    тный
    1.04
     nécessite
    1.03
    POSITIVE LOGITS
    Фі
    0.95
     threw
    0.93
    Ты
    0.93
    Tapi
    0.91
    नम
    0.88
    ).
    0.88
     resemblance
    0.85
    Thy
    0.84
    ಥವಾ
    0.84
    नरी
    0.84
    Act Density 0.001%

    No Known Activations