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

    Neuronpedia

    INDEX
    Explanations

    service provider

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🏗
    0.41
    洧
    0.41
     ইয়াহিয়ার
    0.41
    <unused1112>
    0.41
    ሱስ
    0.41
    片的
    0.41
     ـ
    0.40
     TouchUtils
    0.40
    <unused2050>
    0.40
     有限
    0.39
    POSITIVE LOGITS
    S
    0.60
    SC
    0.47
    SQ
    0.47
     S
    0.47
    SO
    0.47
    s
    0.46
    first
    0.46
    although
    0.46
    SP
    0.46
    encore
    0.45
    Act Density 0.160%

    No Known Activations