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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iosity
    -0.07
    autor
    -0.07
     fare
    -0.07
     Comple
    -0.07
     Optional
    -0.07
    .resolution
    -0.07
    $filter
    -0.07
    shr
    -0.07
    ょう
    -0.07
     profiler
    -0.07
    POSITIVE LOGITS
    활동
    0.07
    새
    0.06
     وقد
    0.06
    077
    0.06
     Sears
    0.05
     Injection
    0.05
    ayız
    0.05
    >";
    0.05
    紅
    0.05
     гол
    0.05
    Act Density 0.109%

    No Known Activations