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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     commotion
    0.46
     awakening
    0.43
     behest
    0.41
     midst
    0.40
     na
    0.40
     manor
    0.40
     pastime
    0.39
     paradigma
    0.38
     bygone
    0.38
     to
    0.38
    POSITIVE LOGITS
    OSITION
    0.42
    ﺎ
    0.40
    ﺰ
    0.38
    ቬ
    0.37
    ﻤ
    0.36
     மற்றும்
    0.35
    YAML
    0.35
    Toplam
    0.35
    Columns
    0.35
    Coupon
    0.34
    Act Density 0.000%

    No Known Activations