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

    Neuronpedia

    INDEX
    Explanations

    options and choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reintegr
    0.45
     zur
    0.42
     ])
    0.40
     -=
    0.40
     folate
    0.39
     Zur
    0.38
    >-</
    0.38
    شنا
    0.38
    amate
    0.38
     kube
    0.38
    POSITIVE LOGITS
    statistical
    0.42
     покупа
    0.41
    渀
    0.40
    ctuations
    0.40
    ᅡ
    0.39
     opções
    0.39
     вариант
    0.38
     ಅವಕಾಶ
    0.38
     بازار
    0.37
    CCCCCCCC
    0.37
    Act Density 0.002%

    No Known Activations