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

    Neuronpedia

    INDEX
    Explanations

    explaining regulation and breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ığımız
    0.50
    ot
    0.47
    erd
    0.46
    ọi
    0.46
    ारक
    0.45
    irdiği
    0.45
    стные
    0.45
    oreau
    0.45
    ol
    0.44
    orea
    0.44
    POSITIVE LOGITS
     predictability
    0.47
     divina
    0.47
    以便
    0.44
    價格
    0.44
     المرسلين
    0.43
     enigma
    0.43
     因為
    0.42
     brutality
    0.42
    現象
    0.42
     alarm
    0.41
    Act Density 0.009%

    No Known Activations