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

    Neuronpedia

    INDEX
    Explanations

    AI research and technical explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Be
    0.65
    obec
    0.65
    BE
    0.65
    ב
    0.63
    Бе
    0.63
     Beads
    0.62
    ബ്
    0.62
     বো
    0.61
     Beiträge
    0.61
    бы
    0.61
    POSITIVE LOGITS
    ର୍
    0.66
     gateway
    0.65
    ციის
    0.64
    слен
    0.63
    éric
    0.62
    ieni
    0.62
     салу
    0.61
     faculties
    0.60
     dynamical
    0.59
     corruption
    0.58
    Act Density 0.186%

    No Known Activations