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

    Neuronpedia

    INDEX
    Explanations

    GPT-4 Turbo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ال
    1.15
     නො
    0.91
    il
    0.91
    الل
    0.90
     це
    0.90
     разум
    0.89
     اور
    0.87
     ك
    0.87
    ч
    0.86
    潾
    0.86
    POSITIVE LOGITS
     interstitiis
    1.38
     imassa
    1.32
     raging
    1.30
     vudd
    1.25
     tattha
    1.23
     gastron
    1.23
     tengamos
    1.22
     conlleva
    1.21
     strikingly
    1.21
    ଐ
    1.20
    Act Density 0.000%

    No Known Activations