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

    Neuronpedia

    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    昙
    -0.08
    Ḟ
    -0.07
    饰
    -0.07
    mse
    -0.07
    成熟的
    -0.07
    )n
    -0.07
    白
    -0.07
     waves
    -0.06
     named
    -0.06
     nec
    -0.06
    POSITIVE LOGITS
     upstairs
    0.07
     dads
    0.07
    —we
    0.07
    GRAM
    0.07
     ########################
    0.07
     East
    0.07
     endlessly
    0.06
     joystick
    0.06
    (condition
    0.06
     UTIL
    0.06
    Act Density 0.001%

    No Known Activations