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

    Neuronpedia

    INDEX
    Explanations

    levels of, amount of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.47
    1.23
    al
    1.05
    s
    1.04
    ot
    1.02
    p
    0.98
    ch
    0.98
    ف
    0.95
    ed
    0.94
     어린
    0.93
    POSITIVE LOGITS
    datast
    1.19
    linkOpacity
    1.12
    Pued
    1.11
     действует
    1.11
     Públic
    1.09
    ர்ச்சி
    1.08
     şekilde
    1.06
     juncture
    1.06
    قى
    1.05
     ओपी
    1.04
    Act Density 0.194%

    No Known Activations