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

    Neuronpedia

    INDEX
    Explanations

    statues and their prohibitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trám
    0.40
     ಕ್ಷೇತ್ರದ
    0.39
     لینا
    0.39
    ୫
    0.39
    ಾಗ
    0.38
     طریقہ
    0.38
     käyt
    0.38
     druż
    0.38
     couv
    0.38
     sélectionnés
    0.38
    POSITIVE LOGITS
    3
    0.42
    itution
    0.39
    l
    0.38
     harmful
    0.38
    +
    0.37
     third
    0.37
     الثالث
    0.37
    ando
    0.37
    -
    0.37
    or
    0.36
    Act Density 0.088%

    No Known Activations