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

    Neuronpedia

    INDEX
    Explanations

    Thermodynamic cycles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discretionary
    -0.08
     £
    -0.08
    ,exports
    -0.07
    exports
    -0.07
     intimate
    -0.07
    یو
    -0.07
     tall
    -0.07
    _bytes
    -0.07
     fees
    -0.07
    heavy
    -0.07
    POSITIVE LOGITS
     ciclo
    0.11
     cycle
    0.10
     цикл
    0.10
     этап
    0.10
     مراحل
    0.10
     cycles
    0.10
    Cycle
    0.10
     ciclos
    0.09
     عمليات
    0.09
    周期
    0.09
    Act Density 0.004%

    No Known Activations