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

    Neuronpedia

    INDEX
    Explanations

    wireless connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.52
     same
    0.45
    upp
    0.45
    opp
    0.45
    Friday
    0.43
     passed
    0.43
     samme
    0.43
     Same
    0.43
     النسبيه
    0.42
     samma
    0.42
    POSITIVE LOGITS
    ໃຫ້
    0.49
    ຢ
    0.49
     пример
    0.48
    Здравствуйте
    0.48
    ﺩ
    0.48
     ба
    0.47
     Sér
    0.46
    ງ
    0.45
     дат
    0.44
     αγ
    0.44
    Act Density 0.001%

    No Known Activations