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

    Neuronpedia

    INDEX
    Explanations

    topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sinus
    -0.07
     '_
    -0.06
    орм
    -0.06
     cemetery
    -0.06
     beg
    -0.06
     Kumar
    -0.06
    قار
    -0.06
    敝
    -0.06
     pause
    -0.06
    ^(
    -0.06
    POSITIVE LOGITS
     incarn
    0.09
    듬
    0.08
    美麗
    0.07
     postId
    0.07
    临沂
    0.07
    过于
    0.07
    (gen
    0.07
     무료
    0.06
     Garrett
    0.06
    лиц
    0.06
    Act Density 0.038%

    No Known Activations