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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "How
    -0.07
    590
    -0.07
     {});↵↵
    -0.07
    èn
    -0.07
    cov
    -0.07
    ACITY
    -0.06
    $num
    -0.06
    \xc
    -0.06
    .NO
    -0.06
    :any
    -0.06
    POSITIVE LOGITS
    ltk
    0.06
    rax
    0.06
    мп
    0.06
    Doing
    0.06
     puts
    0.06
     프로그램
    0.06
     radio
    0.06
    ۱۹۷
    0.06
    наче
    0.06
    Resistance
    0.06
    Act Density 0.017%

    No Known Activations