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

    Neuronpedia

    INDEX
    Explanations

    atmosphere, negation, or specific services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Prove
    0.54
    Ii
    0.52
    GPI
    0.47
    ьи
    0.46
    س
    0.46
    ्
    0.44
    ഗ
    0.44
    numbers
    0.43
    Naive
    0.43
    ReLU
    0.42
    POSITIVE LOGITS
     Beiträge
    0.48
     Consume
    0.46
     వే
    0.45
     농
    0.45
     Fusion
    0.44
    ಾರ್ಟ
    0.44
    ኗ
    0.44
     Rock
    0.43
     Keeping
    0.43
     Во
    0.42
    Act Density 0.003%

    No Known Activations