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

    Neuronpedia

    INDEX
    Explanations

    say ".add"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    讀
    -0.07
     Games
    -0.07
    Regards
    -0.06
    겠습니다
    -0.06
    ΩΣ
    -0.06
    ुष
    -0.06
    بد
    -0.06
    イント
    -0.06
    ää
    -0.06
    ango
    -0.06
    POSITIVE LOGITS
     tearing
    0.07
     broaden
    0.07
     massac
    0.06
     Shapes
    0.06
    \OptionsResolver
    0.06
    .'"
    0.06
     examining
    0.06
     dialogRef
    0.06
     afforded
    0.06
    _CLI
    0.06
    Act Density 0.002%

    No Known Activations