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

    Neuronpedia

    INDEX
    Explanations

    Javascript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XI
    -0.08
    ná
    -0.07
    ąd
    -0.07
    -sample
    -0.06
    	CHECK
    -0.06
     mejores
    -0.06
    èmes
    -0.06
     biomass
    -0.06
    -orders
    -0.06
    'na
    -0.06
    POSITIVE LOGITS
    牛
    0.07
    (adj
    0.06
     perish
    0.06
    _href
    0.06
    ...)↵
    0.06
    稍
    0.06
    Art
    0.06
    Corner
    0.06
    ره
    0.06
     jug
    0.06
    Act Density 0.013%

    No Known Activations