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

    Neuronpedia

    INDEX
    Explanations

    hang up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ring
    0.56
    ng
    0.55
    lands
    0.53
     I
    0.52
    rees
    0.50
     Rules
    0.48
     X
    0.47
    les
    0.46
    ni
    0.46
     इस
    0.45
    POSITIVE LOGITS
    ת
    0.62
    した
    0.55
    단
    0.54
     buoni
    0.52
    파일
    0.52
    پ
    0.52
     phần
    0.51
    คุณ
    0.51
    เขา
    0.51
     کي
    0.51
    Act Density 0.000%

    No Known Activations