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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LOW
    -0.07
    cház
    -0.06
     Rig
    -0.06
    .pkl
    -0.06
    ?>
↵
↵
    -0.06
     Channels
    -0.06
    @WebServlet
    -0.06
    Ž
    -0.06
     disqualified
    -0.06
    22
    -0.06
    POSITIVE LOGITS
    _money
    0.07
     antagonist
    0.07
     handwriting
    0.07
    _partial
    0.06
    аном
    0.06
     Compass
    0.06
     kidnapped
    0.06
     ${
    0.06
    ;",↵
    0.06
     rodin
    0.06
    Act Density 0.058%

    No Known Activations