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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhánh
    -0.07
     Yan
    -0.07
    hus
    -0.06
    -git
    -0.06
    anceled
    -0.06
    ností
    -0.06
     COPYRIGHT
    -0.06
     Kot
    -0.06
    	get
    -0.06
    Opens
    -0.06
    POSITIVE LOGITS
    Favorite
    0.06
    ught
    0.06
    -sample
    0.06
    GBP
    0.06
     Том
    0.06
    씀
    0.06
     معل
    0.06
     zahl
    0.06
    _CBC
    0.06
     counselling
    0.06
    Act Density 0.121%

    No Known Activations