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

    Neuronpedia

    INDEX
    Explanations

    adventures, parts, B.P., Exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    쭌
    1.29
     persone
    1.23
    ™.
    1.20
     activid
    1.19
     aula
    1.17
    Sofia
    1.16
     Milano
    1.15
    诸多
    1.13
    STRU
    1.12
    ഓം
    1.12
    POSITIVE LOGITS
    ம்
    1.27
    m
    1.20
    ू
    1.13
    ే
    1.12
    lly
    1.11
    л
    1.11
    z
    1.10
     doesn
    1.07
    k
    1.06
    al
    1.05
    Act Density 0.001%

    No Known Activations