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

    Neuronpedia

    INDEX
    Explanations

    multiple languages and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lari
    1.15
    k
    1.07
    te
    0.97
    r
    0.95
     exposé
    0.95
    n
    0.91
    ties
    0.90
    ن
    0.90
    lide
    0.90
    लया
    0.90
    POSITIVE LOGITS
     in
    1.55
    ও
    1.40
     في
    1.37
    在
    1.34
     σε
    1.29
    も
    1.29
    도
    1.27
    3
    1.09
     در
    1.02
    ۳
    1.00
    Act Density 0.000%

    No Known Activations