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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     famous
    -0.07
    -example
    -0.06
    Emergency
    -0.06
     scenic
    -0.06
     Voice
    -0.06
    +r
    -0.06
     insan
    -0.06
     HUD
    -0.06
    ितन
    -0.06
    	utils
    -0.06
    POSITIVE LOGITS
    cta
    0.07
     дозвол
    0.06
    θν
    0.06
    ременно
    0.06
     їх
    0.06
    classList
    0.06
     возмож
    0.06
     Peg
    0.06
     Dolphin
    0.06
     foster
    0.06
    Act Density 0.031%

    No Known Activations