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

    Neuronpedia

    INDEX
    Explanations

    creation and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    分别是
    0.38
    ↵
    0.38
     podczas
    0.36
     এপ্রিল
    0.36
     during
    0.36
     апре
    0.35
     actualizada
    0.35
     dưới
    0.35
     bowiem
    0.35
    সজ্জিত
    0.35
    POSITIVE LOGITS
    នាំ
    0.41
     glories
    0.41
    걍
    0.41
     outright
    0.41
     entier
    0.40
    0.39
     prot
    0.39
     ett
    0.39
     bigger
    0.39
    Algo
    0.39
    Act Density 0.010%

    No Known Activations