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

    Neuronpedia

    INDEX
    Explanations

    code/version strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fac
    -0.07
    棋
    -0.07
    	location
    -0.07
     основном
    -0.06
    접
    -0.06
     Atmospheric
    -0.06
     입
    -0.06
    (heap
    -0.06
    _turn
    -0.06
    enc
    -0.06
    POSITIVE LOGITS
    prav
    0.06
     unnatural
    0.06
     SSR
    0.06
    /models
    0.06
     fears
    0.06
    ocurrency
    0.06
    itti
    0.06
     __________________________________
    0.06
     thời
    0.06
    iteur
    0.06
    Act Density 0.059%

    No Known Activations