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

    Neuronpedia

    INDEX
    Explanations

    Neural network layers code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "}\
    -0.09
     "));↵
    -0.08
    .openConnection
    -0.07
     microbes
    -0.07
    (decoded
    -0.07
    ombre
    -0.07
    (""));↵
    -0.07
    ></
    -0.07
    /",
    -0.07
    킥
    -0.07
    POSITIVE LOGITS
    mq
    0.07
    edb
    0.07
     coolest
    0.07
    yr
    0.07
     trajectories
    0.06
    few
    0.06
    德国
    0.06
    _it
    0.06
    تصرف
    0.06
    ern
    0.06
    Act Density 0.003%

    No Known Activations