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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IndexChanged
    -0.07
    ="#">
    -0.06
     setTitle
    -0.06
    ENAME
    -0.06
     Argentine
    -0.06
    íně
    -0.06
    ACK
    -0.06
    Admin
    -0.06
    .lucene
    -0.06
     suc
    -0.06
    POSITIVE LOGITS
    (SS
    0.07
     connects
    0.06
    _answers
    0.06
    َك
    0.06
    测试
    0.06
     을
    0.06
    (world
    0.06
     spilled
    0.06
    _str
    0.06
    ży
    0.06
    Act Density 0.219%

    No Known Activations