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

    Neuronpedia

    INDEX
    Explanations

    angle

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    想
    -0.07
     nud
    -0.07
     dancers
    -0.07
    PTH
    -0.06
    ("");
    -0.06
     影
    -0.06
    (Student
    -0.06
     Psychology
    -0.06
     CLOCK
    -0.06
     CZ
    -0.06
    POSITIVE LOGITS
     masih
    0.06
     Earn
    0.06
    ěr
    0.06
     र
    0.06
     Combine
    0.06
    ự
    0.06
    visit
    0.06
     earrings
    0.06
    using
    0.06
    -loaded
    0.06
    Act Density 0.102%

    No Known Activations