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

    Neuronpedia

    INDEX
    Explanations

    simulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Collie
    0.68
     múlti
    0.67
     gulp
    0.63
     convent
    0.61
     singlet
    0.61
    வ்வேறு
    0.60
     Cartan
    0.57
     collie
    0.57
     Collier
    0.57
    年から
    0.56
    POSITIVE LOGITS
    ش
    0.81
    kita
    0.75
    étaient
    0.73
    k
    0.70
    videos
    0.68
     দুর্ঘটনার
    0.66
    aba
    0.65
    andelions
    0.65
    ه‌های
    0.64
    ě
    0.64
    Act Density 0.003%

    No Known Activations