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

    Neuronpedia

    INDEX
    Explanations

    itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     istiyorum
    0.47
     مجھے
    0.45
    Laravel
    0.44
     》
    0.42
     conteudo
    0.41
    larını
    0.41
     Bismillahirrah
    0.41
    实质
    0.40
    ución
    0.39
    髯
    0.39
    POSITIVE LOGITS
    เมื่อ
    0.43
    ice
    0.42
    స్తాయి
    0.42
     when
    0.42
    NEWS
    0.41
    qu
    0.40
     каждую
    0.39
     intervalles
    0.39
     aided
    0.39
    ng
    0.39
    Act Density 0.000%

    No Known Activations