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

    Neuronpedia

    INDEX
    Explanations

    Manoa Falls, dishonest, orangutan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    는
    1.28
    л
    1.26
    は
    1.23
    합
    1.20
    은
    1.19
     lluvias
    1.18
     upholstered
    1.16
    н
    1.15
    по
    1.14
    같이
    1.14
    POSITIVE LOGITS
    den
    1.12
    ry
    1.05
    dc
    1.05
    ↵↵
    1.05
    dal
    1.02
    ders
    1.00
    de
    0.98
    daten
    0.95
    dj
    0.95
    dh
    0.94
    Act Density 0.000%

    No Known Activations