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

    Neuronpedia

    INDEX
    Explanations

    probability questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stderr
    -0.07
     filler
    -0.07
    	If
    -0.07
    400
    -0.07
     spont
    -0.06
    �
    -0.06
     sucks
    -0.06
     ikke
    -0.06
    PropTypes
    -0.06
    _SEG
    -0.06
    POSITIVE LOGITS
    uel
    0.06
    ophage
    0.06
    科学
    0.06
     Mumbai
    0.06
     реб
    0.06
     TLabel
    0.06
    engkap
    0.06
    );\
    0.06
    olicit
    0.06
    	Item
    0.06
    Act Density 0.004%

    No Known Activations