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

    Neuronpedia

    INDEX
    Explanations

    certain followed by themes/fantasies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.24
     intérieure
    1.15
     Tú
    1.09
     što
    1.08
    F
    1.08
     PAOK
    1.07
     gamme
    1.06
     légère
    1.05
     ký
    1.04
    يتر
    1.03
    POSITIVE LOGITS
    ’
    1.72
    on
    1.53
    en
    1.31
    ang
    1.20
    certain
    1.17
    ana
    1.09
    ا
    1.09
    ater
    1.05
    ied
    1.05
    in
    1.04
    Act Density 0.125%

    No Known Activations