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

    Neuronpedia

    INDEX
    Explanations

    say "ide"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ौन
    -0.07
     player
    -0.07
    [keys
    -0.06
    иться
    -0.06
    =context
    -0.06
     Одна
    -0.06
    uyễn
    -0.06
    İR
    -0.06
     отмеч
    -0.06
     alternatives
    -0.06
    POSITIVE LOGITS
     SON
    0.06
     재
    0.06
    _met
    0.06
    mlink
    0.06
    .as
    0.06
    latitude
    0.06
     �
    0.06
     Γκ
    0.06
    ㅋㅋ
    0.06
    Phase
    0.06
    Act Density 0.001%

    No Known Activations