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

    Neuronpedia

    INDEX
    Explanations

    financial numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hefty
    -0.07
     libraries
    -0.07
    ados
    -0.06
    ovou
    -0.06
     responding
    -0.06
    Circle
    -0.06
    	opt
    -0.06
     roll
    -0.06
     aut
    -0.06
     releases
    -0.06
    POSITIVE LOGITS
     Ways
    0.07
    _APP
    0.07
    elf
    0.07
     thảo
    0.06
     tratt
    0.06
    、“
    0.06
     gerekiyor
    0.06
    Fullscreen
    0.06
     فل
    0.06
    かけ
    0.06
    Act Density 0.023%

    No Known Activations