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

    Neuronpedia

    INDEX
    Explanations

    words or code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    °,
    0.42
    isted
    0.41
    ampil
    0.40
    iri
    0.39
    oncé
    0.39
    ik
    0.39
     Muir
    0.38
    ähr
    0.38
    ither
    0.38
    ፊ
    0.38
    POSITIVE LOGITS
     ग्लोबल
    0.44
    messe
    0.43
     problemlos
    0.43
     (=
    0.42
    (
    0.42
     महंगा
    0.41
     schnell
    0.41
     NodeJS
    0.41
    ٹو
    0.41
     शीघ्र
    0.40
    Act Density 0.003%

    No Known Activations