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

    Neuronpedia

    INDEX
    Explanations

    legal rights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hora
    -0.07
    .Email
    -0.07
     amber
    -0.06
     blatant
    -0.06
     khám
    -0.06
     Masks
    -0.06
    ím
    -0.06
     Hogwarts
    -0.06
    eným
    -0.06
     Medicaid
    -0.06
    POSITIVE LOGITS
    ElapsedTime
    0.06
    ürlich
    0.06
     useContext
    0.06
    еліг
    0.06
     explaining
    0.06
    (rs
    0.06
    cycle
    0.06
     GameManager
    0.06
     kleine
    0.06
     ایران
    0.06
    Act Density 0.067%

    No Known Activations