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

    Neuronpedia

    INDEX
    Explanations

    horse racing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reflection
    -0.07
     Normally
    -0.07
    istro
    -0.07
    _scroll
    -0.07
     pounding
    -0.07
    Pop
    -0.06
     Hil
    -0.06
    watch
    -0.06
    exit
    -0.06
     Turtle
    -0.06
    POSITIVE LOGITS
     jpg
    0.07
    护
    0.07
     Em
    0.06
     těchto
    0.06
    libc
    0.06
     erotik
    0.06
    全面
    0.06
    532
    0.06
     množství
    0.06
    Missing
    0.06
    Act Density 0.004%

    No Known Activations