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

    Neuronpedia

    INDEX
    Explanations

    assignment in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ((
    1.36
     +(
    1.18
    ((
    1.13
    ूब
    1.07
     Ok
    1.06
     {(
    1.06
     (
    1.03
     "(
    1.02
     ok
    1.01
    र्फ
    1.01
    POSITIVE LOGITS
    ে
    1.56
    ാ
    1.53
    aac
    1.35
    aas
    1.30
    a
    1.30
    ѡ
    1.29
    лля
    1.25
    нга
    1.19
    guj
    1.19
    auml
    1.19
    Act Density 0.001%

    No Known Activations