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

    Neuronpedia

    INDEX
    Explanations

    allege

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rende
    -0.07
    etails
    -0.07
    缺
    -0.06
    ニニ
    -0.06
    Ptr
    -0.06
    -await
    -0.06
     ／:
    -0.06
    еним
    -0.06
    ANJI
    -0.06
    /view
    -0.06
    POSITIVE LOGITS
     wears
    0.07
     News
    0.07
    **(
    0.06
     healthier
    0.06
     signaled
    0.06
     ```
    0.06
    汉
    0.06
     minister
    0.06
     generalized
    0.06
     Ter
    0.06
    Act Density 0.011%

    No Known Activations