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

    Neuronpedia

    INDEX
    Explanations

    reach out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bots
    0.68
     recommandée
    0.67
     ग
    0.66
     ጥ
    0.64
     exponencial
    0.63
     Echo
    0.62
     meditate
    0.61
    bot
    0.61
     पती
    0.61
     ref
    0.60
    POSITIVE LOGITS
    ath
    0.67
    arze
    0.64
    اتھ
    0.64
     coils
    0.61
    aven
    0.61
     কাশ্মীর
    0.61
    اة
    0.59
    dead
    0.58
    érée
    0.58
    cela
    0.58
    Act Density 0.007%

    No Known Activations