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

    Neuronpedia

    INDEX
    Explanations

    end of text marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tır
    1.00
    ﺎ
    1.00
    ्स
    0.92
    speople
    0.91
    tir
    0.90
    s
    0.89
    TO
    0.88
    ATE
    0.86
    tis
    0.86
    tion
    0.86
    POSITIVE LOGITS
    gunaan
    0.86
     Huyền
    0.84
     vaše
    0.72
    encias
    0.70
     lâm
    0.70
    otional
    0.70
    letzt
    0.69
     chờ
    0.69
     thở
    0.69
     Saltar
    0.69
    Act Density 0.081%

    No Known Activations