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

    Neuronpedia

    INDEX
    Explanations

    welding and weld symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    1.02
    of
    0.88
    ur
    0.88
    f
    0.84
    um
    0.82
    it
    0.80
    ari
    0.78
    p
    0.77
    im
    0.76
    ى
    0.76
    POSITIVE LOGITS
    ת
    0.94
    ל
    0.93
     welds
    0.90
     свар
    0.84
    ل
    0.77
     welding
    0.76
    ล
    0.74
    ↵
    0.73
     Welding
    0.72
    焊接
    0.68
    Act Density 0.001%

    No Known Activations