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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _paint
    -0.07
     approached
    -0.06
     zorunda
    -0.06
     Nội
    -0.06
    只能
    -0.06
    zap
    -0.06
    ]);↵
    -0.06
     departamento
    -0.06
     Joh
    -0.06
     banquet
    -0.06
    POSITIVE LOGITS
     snag
    0.07
     forEach
    0.06
    _instances
    0.06
    Benchmark
    0.06
    PTION
    0.06
     هاي
    0.06
    productive
    0.06
     مدیر
    0.06
     Providence
    0.06
     abusive
    0.06
    Act Density 0.006%

    No Known Activations