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

    Neuronpedia

    INDEX
    Explanations

    Brake lines and cables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     repetition
    -0.09
    You
    -0.08
    Down
    -0.07
    Explanation
    -0.07
     achievable
    -0.07
     downward
    -0.07
    Charsets
    -0.07
    ARDS
    -0.07
     mortality
    -0.07
    Response
    -0.07
    POSITIVE LOGITS
    лох
    0.08
    /cart
    0.08
    (sl
    0.07
    填写
    0.07
    istro
    0.07
     конфликт
    0.07
     dgv
    0.07
     సమావేశ
    0.07
    leck
    0.07
     nyl
    0.07
    Act Density 0.006%

    No Known Activations