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

    Neuronpedia

    INDEX
    Explanations

    vector representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     οι
    0.46
    astas
    0.45
     ليست
    0.45
     التن
    0.44
     !")
    0.43
     étudiants
    0.43
     ધો
    0.43
    é
    0.43
     עם
    0.43
    getCharAt
    0.43
    POSITIVE LOGITS
    ни
    0.46
     P
    0.43
     Potter
    0.43
    ний
    0.42
    SetUp
    0.40
     Dusk
    0.40
     Old
    0.39
    ’
    0.39
    ove
    0.39
     St
    0.39
    Act Density 0.002%

    No Known Activations