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

    Neuronpedia

    INDEX
    Explanations

    confidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अनुभव
    0.82
     It
    0.80
    diabetes
    0.77
    kers
    0.75
    nen
    0.73
    awt
    0.72
    inians
    0.72
     अक्ष
    0.72
     армии
    0.70
     измерения
    0.70
    POSITIVE LOGITS
     confidence
    1.32
    et
    1.29
    i
    1.27
    in
    1.19
    ↵
    1.15
    ר
    1.14
    ad
    1.13
     confident
    1.05
     Confidence
    1.03
    e
    1.03
    Act Density 0.043%

    No Known Activations