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

    Neuronpedia

    INDEX
    Explanations

    food ingredients, drugs, chemical elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ऐसी
    0.64
    ιδ
    0.62
    อน
    0.61
    وت
    0.59
     ला
    0.57
     좋아
    0.57
     जिसके
    0.55
    ExpNow
    0.54
    ियोजना
    0.53
    بان
    0.52
    POSITIVE LOGITS
    x
    0.89
    </b>
    0.86
    n
    0.77
    <0x0D>
    0.74
    -
    0.72
    ponsors
    0.71
    0.71
    ,
    0.71
     temel
    0.70
    য়ের
    0.67
    Act Density 0.045%

    No Known Activations