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

    Neuronpedia

    INDEX
    Explanations

    "and" or "or" conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     téléphon
    0.45
     Murphy
    0.45
     técnicos
    0.44
     Léon
    0.44
     McKinsey
    0.43
    逊
    0.43
    𢎞
    0.43
    สิน
    0.43
    ریم
    0.43
     controles
    0.43
    POSITIVE LOGITS
     или
    0.54
     কিংবা
    0.52
     અને
    0.52
    tor
    0.50
     և
    0.50
    such
    0.50
     и
    0.49
    или
    0.48
     și
    0.48
    や
    0.48
    Act Density 0.009%

    No Known Activations