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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ACT
    -0.08
    .carousel
    -0.07
    .Constant
    -0.07
    "<<
    -0.06
    uilt
    -0.06
    /");↵
    -0.06
    PLAN
    -0.06
    ']}↵
    -0.06
     ->↵
    -0.06
     })();↵
    -0.06
    POSITIVE LOGITS
     loài
    0.07
    rieving
    0.07
     เ
    0.06
    анд
    0.06
    /popper
    0.06
     bullshit
    0.06
    Produces
    0.06
    аю
    0.06
     şekilde
    0.06
     Budapest
    0.06
    Act Density 0.234%

    No Known Activations