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

    Neuronpedia

    INDEX
    Explanations

    but it's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಿದ್ದಾನೆ
    0.48
    টো
    0.46
     PREMIUM
    0.45
     sprawie
    0.44
     Motel
    0.43
     حتی
    0.43
     buil
    0.42
     couvrir
    0.41
     baggy
    0.41
    ceral
    0.40
    POSITIVE LOGITS
    Anton
    0.48
    Greetings
    0.43
    0.43
    Friends
    0.43
    Nickname
    0.42
    Has
    0.41
    abulary
    0.41
    Anthony
    0.41
    Unit
    0.40
    Read
    0.40
    Act Density 0.068%

    No Known Activations