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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mario
    -0.07
    캥
    -0.07
     %>
    -0.07
    Ї
    -0.07
    _profit
    -0.07
    <Course
    -0.07
    _probe
    -0.07
    étranger
    -0.07
     عنه
    -0.07
    ();?>
    -0.07
    POSITIVE LOGITS
    ':
    0.07
    亮点
    0.07
    队员们
    0.07
     Revolution
    0.07
     Ink
    0.07
    ":
    0.07
    违背
    0.07
     Sou
    0.07
     tuyến
    0.07
    できて
    0.06
    Act Density 0.067%

    No Known Activations