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

    Neuronpedia

    INDEX
    Explanations

    clarifying questions for suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    btn
    0.81
    cdot
    0.74
    Write
    0.73
    add
    0.73
    narr
    0.73
    膚
    0.73
    write
    0.72
     write
    0.72
    ester
    0.72
    ခန်း
    0.72
    POSITIVE LOGITS
     caveat
    0.88
     OMS
    0.84
     Origin
    0.83
     JIS
    0.79
     Quando
    0.78
     CNG
    0.77
     rarely
    0.77
     NCS
    0.76
     AttributeError
    0.76
    Origin
    0.76
    Act Density 0.013%

    No Known Activations