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

    Neuronpedia

    INDEX
    Explanations

    AI delivering on promises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ක්
    0.41
     jusqu
    0.41
     spineItem
    0.41
     nrow
    0.40
     confining
    0.39
    until
    0.38
    retirement
    0.38
     Transactions
    0.38
     noires
    0.38
     Until
    0.38
    POSITIVE LOGITS
     —
    0.41
    وسی
    0.40
     sở
    0.38
    Slash
    0.38
     slander
    0.38
    Reco
    0.37
    架
    0.37
     मेड
    0.37
    Mesh
    0.37
    पुरी
    0.37
    Act Density 0.000%

    No Known Activations