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

    Neuronpedia

    INDEX
    Explanations

    where keys go

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ingrese
    0.38
     vean
    0.38
    퐫
    0.38
    🥙
    0.38
    ⵕ
    0.38
     Pseudomonas
    0.38
    駙
    0.37
    кий
    0.37
    بيض
    0.37
     Lactobacillus
    0.37
    POSITIVE LOGITS
     edizione
    0.42
     arbitrarily
    0.41
     reserves
    0.39
    edition
    0.37
     malam
    0.36
     arbitrary
    0.36
     subtraction
    0.36
     enn
    0.35
    нун
    0.35
     edición
    0.35
    Act Density 0.000%

    No Known Activations