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

    Neuronpedia

    INDEX
    Explanations

    partitioning index

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ഫോ
    0.40
     ಪರಿಸ
    0.40
    Ordinary
    0.38
     ভিডি
    0.38
    achadh
    0.38
    FieldValue
    0.37
    Salmon
    0.37
    覀
    0.37
    AZIONE
    0.36
    ierta
    0.36
    POSITIVE LOGITS
     типу
    0.44
    类型的
    0.43
     Кы
    0.43
     Nanjing
    0.42
     bisexual
    0.41
    boss
    0.37
    োজ
    0.37
    ليز
    0.37
    hei
    0.37
    பர
    0.37
    Act Density 0.000%

    No Known Activations