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

    Neuronpedia

    INDEX
    Explanations

    competition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ildiği
    -0.08
     timid
    -0.07
     TOTAL
    -0.07
    랑
    -0.06
    :^{↵
    -0.06
     Lib
    -0.06
    ському
    -0.06
    せて
    -0.06
    форма
    -0.06
    _seed
    -0.06
    POSITIVE LOGITS
    CLIENT
    0.06
     tradi
    0.06
     الصن
    0.06
    (samples
    0.06
     куб
    0.06
     proble
    0.06
    áln
    0.06
     Floral
    0.06
    tok
    0.06
     تخصص
    0.06
    Act Density 0.013%

    No Known Activations