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

    Neuronpedia

    INDEX
    Explanations

    onCreate, creation, uranium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.25
    r
    1.23
    ong
    1.19
    ia
    1.05
    z
    0.95
    u
    0.86
    d
    0.84
    ow
    0.83
    al
    0.82
    em
    0.82
    POSITIVE LOGITS
    ق
    1.21
    ни
    1.03
    ש
    0.87
     to
    0.87
    б
    0.82
    логи
    0.80
     at
    0.79
    いました
    0.79
    во
    0.76
    した
    0.76
    Act Density 0.000%

    No Known Activations