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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вмі
    -0.06
    杰
    -0.06
    oriasis
    -0.06
    欣
    -0.06
    _mas
    -0.06
    employees
    -0.06
     productId
    -0.06
    >());↵↵
    -0.06
    jun
    -0.06
    히
    -0.06
    POSITIVE LOGITS
    CurrentUser
    0.07
    الى
    0.06
     проти
    0.06
    ancellor
    0.06
    alias
    0.06
    reopen
    0.06
    ...'
    0.06
    _ENC
    0.06
     scorer
    0.06
     清
    0.06
    Act Density 0.056%

    No Known Activations