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

    Neuronpedia

    INDEX
    Explanations

    derivative questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Members
    -0.08
    네
    -0.07
    responses
    -0.07
    urrenc
    -0.06
     Abdel
    -0.06
     ;-
    -0.06
    isper
    -0.06
    008
    -0.06
    Lexer
    -0.06
    '.↵
    -0.06
    POSITIVE LOGITS
     MyClass
    0.06
     VI
    0.06
    (bottom
    0.06
     ofs
    0.06
    MEDIA
    0.06
    «
    0.06
     ül
    0.06
    _DEF
    0.06
     Saint
    0.06
     самостоятельно
    0.06
    Act Density 0.019%

    No Known Activations