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

    Neuronpedia

    INDEX
    Explanations

    common english words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fon
    -0.07
    �乐
    -0.06
    ？”↵↵
    -0.06
    {o
    -0.06
     både
    -0.06
     Česko
    -0.06
     politic
    -0.06
     Saudis
    -0.06
    æk
    -0.06
    'en
    -0.06
    POSITIVE LOGITS
     investigating
    0.06
     KR
    0.06
     inquiries
    0.06
    _references
    0.06
    asics
    0.06
    ается
    0.06
    ुध
    0.06
     numRows
    0.06
    _hash
    0.06
    ได
    0.06
    Act Density 0.094%

    No Known Activations