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

    Neuronpedia

    INDEX
    Explanations

    how to access ChatGPT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Verifier
    0.45
    माणे
    0.44
    الب
    0.42
    प्र
    0.41
     undec
    0.41
    چ
    0.41
     internacional
    0.40
     verific
    0.39
    إ
    0.39
    为了
    0.39
    POSITIVE LOGITS
    amantha
    0.53
    alz
    0.48
    uyến
    0.47
    berapa
    0.46
     अच्छी
    0.46
     фонбет
    0.46
    át
    0.45
     Ambris
    0.45
     withholding
    0.44
    confident
    0.44
    Act Density 0.001%

    No Known Activations