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

    Neuronpedia

    INDEX
    Explanations

    recurring motifs or siblings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ICT
    0.34
    ('${
    0.34
    sync
    0.32
    Đ
    0.32
    시간
    0.32
    ONE
    0.31
    ºC
    0.31
    nto
    0.31
    モバイル
    0.30
    oncer
    0.30
    POSITIVE LOGITS
     Foreground
    0.37
     よ
    0.36
     నేపథ
    0.32
     Value
    0.32
     实
    0.32
    தார
    0.32
     אחר
    0.32
     سته
    0.32
     இர
    0.32
     دیگر
    0.32
    Act Density 0.000%

    No Known Activations