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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝖘
    0.44
     könnt
    0.43
     réception
    0.43
    サン
    0.42
    憤
    0.41
     तुम्हाला
    0.41
     l
    0.40
     Whit
    0.40
    ્યૂ
    0.40
    罰
    0.40
    POSITIVE LOGITS
     Créd
    0.39
     credits
    0.38
    enzen
    0.37
    ogar
    0.37
    ায়ক
    0.37
    PrivateKey
    0.36
     writs
    0.36
     knelt
    0.35
     విధంగా
    0.35
     variation
    0.34
    Act Density 0.002%

    No Known Activations