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

    Neuronpedia

    INDEX
    Explanations

    cuda or cpu device

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kinney
    0.34
    ้อย
    0.30
    갤
    0.30
    ኛውም
    0.29
     نفسي
    0.29
     assistants
    0.28
    WARF
    0.28
     الخمسه
    0.27
    ','%
    0.27
     chopsticks
    0.27
    POSITIVE LOGITS
    login
    0.34
     apuesta
    0.34
    download
    0.33
    edas
    0.32
     Passe
    0.32
     Спорттук
    0.31
    password
    0.31
    astia
    0.31
    Compra
    0.31
     compra
    0.31
    Act Density 0.000%

    No Known Activations