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

    Neuronpedia

    INDEX
    Explanations

    if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     În
    1.35
     Dacă
    1.31
     unsur
    1.30
     kemampuan
    1.30
     También
    1.29
     précis
    1.25
     Também
    1.25
     Enquanto
    1.24
     cenário
    1.21
     egy
    1.20
    POSITIVE LOGITS
    re
    1.15
    de
    1.08
    util
    1.05
    true
    1.04
    b
    1.03
    cos
    1.02
    !`
    1.01
    v
    1.00
    visible
    0.99
    get
    0.98
    Act Density 0.200%

    No Known Activations