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

    Neuronpedia

    INDEX
    Explanations

    silent creep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рое
    0.40
    👪
    0.39
    غه
    0.36
    官员
    0.34
     nodeId
    0.34
    ড়াল
    0.34
    捂
    0.34
    reset
    0.33
     প্রবাহ
    0.33
    swiper
    0.33
    POSITIVE LOGITS
    fico
    0.44
    すぎ
    0.40
    スナー
    0.38
     CAPS
    0.38
    Ꮑ
    0.38
    )(((
    0.36
     counseling
    0.36
     посо
    0.36
     மாதிர
    0.36
    యే
    0.35
    Act Density 0.000%

    No Known Activations