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

    Neuronpedia

    INDEX
    Explanations

    Definitions and sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	INNER
    -0.07
    往
    -0.07
    Connor
    -0.07
    oeff
    -0.06
    Kir
    -0.06
    .utils
    -0.06
     oasis
    -0.06
    vana
    -0.06
     anus
    -0.06
    .Axis
    -0.06
    POSITIVE LOGITS
     repeat
    0.07
    Repeat
    0.07
    主力
    0.07
    _interrupt
    0.07
    failed
    0.07
    تحقق
    0.07
    ){
↵
↵
    0.07
     Facts
    0.07
    REPORT
    0.07
     slashing
    0.07
    Act Density 0.041%

    No Known Activations