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

    Neuronpedia

    INDEX
    Explanations

    DeFi specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.84
     बढ़ाया
    0.59
     TextAlign
    0.57
    .?
    0.55
    <unused295>
    0.54
     Faculties
    0.53
    enity
    0.52
    decorated
    0.52
     वर्षों
    0.51
    ,?
    0.50
    POSITIVE LOGITS
    ה
    0.60
    Wol
    0.54
    Bre
    0.52
     surf
    0.52
    Sak
    0.52
    Cox
    0.52
    Murphy
    0.51
    Sie
    0.50
    벤트
    0.50
    ઠા
    0.50
    Act Density 0.000%

    No Known Activations