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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     favour
    -0.08
     Tuesday
    -0.08
     week
    -0.08
     gamble
    -0.07
    -selection
    -0.07
    Saturday
    -0.07
     exam
    -0.07
    費
    -0.07
    "[
    -0.07
     European
    -0.07
    POSITIVE LOGITS
    -unstyled
    0.07
    的理想
    0.07
     defaultMessage
    0.07
    stdint
    0.07
    只想
    0.07
    枍
    0.07
     PH
    0.07
    鸤
    0.07
    odzi
    0.07
    ⇃
    0.07
    Act Density 0.007%

    No Known Activations