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

    Neuronpedia

    INDEX
    Explanations

    hard to explain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    1.58
    (
    1.52
    }$
    1.45
    cient
    1.44
    ihilation
    1.44
    *
    1.41
    pecific
    1.41
    garakan
    1.36
    ées
    1.35
    érêt
    1.35
    POSITIVE LOGITS
     khăn
    1.41
    ᆺ
    1.38
     Besonders
    1.36
    Чтобы
    1.30
     สืบค้นเมื่อ
    1.30
    Кто
    1.26
     majeure
    1.25
     Mukesh
    1.24
    टीएम
    1.23
    IDAY
    1.20
    Act Density 0.290%

    No Known Activations