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

    Neuronpedia

    INDEX
    Explanations

    health information links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    测量
    0.66
    줍니다
    0.64
     себя
    0.64
     Hubbard
    0.63
    រប
    0.62
     Maintenance
    0.62
     लगाएं
    0.62
     Ib
    0.62
     Us
    0.61
    iflower
    0.61
    POSITIVE LOGITS
     नाइट्र
    0.79
    čius
    0.73
    perate
    0.71
    anceled
    0.70
    protein
    0.69
    pered
    0.69
    Intersect
    0.68
    ছুর
    0.67
    गाव
    0.66
     crescendo
    0.66
    Act Density 0.001%

    No Known Activations