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

    Neuronpedia

    INDEX
    Explanations

    cur, cure, cursor, curl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.85
    ת
    0.79
    ir
    0.73
     extender
    0.71
    ன்
    0.66
    น
    0.66
     financi
    0.63
     Vulcan
    0.63
    ہ
    0.63
    it
    0.63
    POSITIVE LOGITS
    9
    0.81
    enin
    0.78
    cur
    0.73
    riculum
    0.72
     кури
    0.72
     Curiosity
    0.70
     ۸
    0.68
    ৯
    0.68
    大
    0.67
     curate
    0.66
    Act Density 0.041%

    No Known Activations