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

    Neuronpedia

    INDEX
    Explanations

    guns, movies, resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্বেও
    0.50
    ensington
    0.47
    ര്യ
    0.45
     দেখেছিলেন
    0.44
    ajian
    0.43
    इसी
    0.43
     нельзя
    0.42
    不能为空
    0.41
     longueur
    0.40
     Judaism
    0.39
    POSITIVE LOGITS
    ක
    0.49
    ல
    0.45
    ก
    0.44
    ت
    0.44
    kak
    0.44
    𝒹
    0.43
     nehmen
    0.43
     usadas
    0.43
    genommen
    0.42
    gür
    0.42
    Act Density 0.000%

    No Known Activations