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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     точно
    -0.10
    ूद
    -0.09
     Occasionally
    -0.09
     gratuitement
    -0.09
     $('
    -0.09
     heater
    -0.09
     Assistance
    -0.09
     nagp
    -0.09
     DETAILS
    -0.08
    อยู่
    -0.08
    POSITIVE LOGITS
     theory
    0.15
     theories
    0.15
    Theory
    0.14
     Theory
    0.13
    理论
    0.10
     teor
    0.10
     théorie
    0.10
     теория
    0.10
     نظری
    0.10
     theorie
    0.09
    Act Density 0.038%

    No Known Activations