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

    Neuronpedia

    INDEX
    Explanations

    shared experiences and family members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     antaranya
    0.18
     ऐप
    0.18
    asadd
    0.18
     yesterday
    0.17
     ఉన్నారు
    0.17
    età
    0.17
     dalamnya
    0.17
     பெற்றது
    0.17
    दलीय
    0.17
    mıştı
    0.17
    POSITIVE LOGITS
    attacks
    0.18
    emi
    0.17
    適切
    0.17
    ảm
    0.16
     ც
    0.16
    ிலோ
    0.16
    (-)
    0.16
    plo
    0.16
    ulasi
    0.16
    সম
    0.16
    Act Density 0.001%

    No Known Activations