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

    Neuronpedia

    INDEX
    Explanations

    choose your adventure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.73
     in
    0.67
    İR
    0.67
    Ь
    0.67
    IBILITY
    0.61
    ร
    0.61
    ៤
    0.61
     способность
    0.60
     patente
    0.60
     herb
    0.58
    POSITIVE LOGITS
    on
    1.13
    d
    1.04
    m
    0.99
    c
    0.98
    p
    0.94
    i
    0.91
    in
    0.89
    al
    0.87
    n
    0.86
    k
    0.86
    Act Density 0.000%

    No Known Activations