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

    Neuronpedia

    INDEX
    Explanations

    programming code and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    对于
    0.44
    Triplet
    0.43
    子
    0.39
     dhe
    0.38
     Trio
    0.38
     triplets
    0.38
     ו
    0.38
    需要
    0.37
    全国
    0.37
    রোগ
    0.36
    POSITIVE LOGITS
     opérés
    0.41
     кон
    0.40
     ordained
    0.40
    stato
    0.39
     холоди
    0.38
    विजन
    0.38
     Tone
    0.38
     signé
    0.38
    )]:
    0.37
     dúvida
    0.37
    Act Density 0.010%

    No Known Activations