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

    Neuronpedia

    INDEX
    Explanations

    amounts and servings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     انف
    0.43
     बौद्ध
    0.41
     διε
    0.41
    kirche
    0.40
     Ανα
    0.40
     நவீன
    0.40
     अबू
    0.40
     бъ
    0.39
    复杂
    0.39
    종
    0.39
    POSITIVE LOGITS
     refills
    0.76
     refill
    0.66
     consumo
    0.65
     servings
    0.64
     quantity
    0.63
     qty
    0.62
     quantities
    0.61
     consumption
    0.60
     количество
    0.59
     deplete
    0.59
    Act Density 0.128%

    No Known Activations