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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    335
    -0.06
    	transform
    -0.06
     }.
    -0.06
    	assertEquals
    -0.06
     paramMap
    -0.06
     Romero
    -0.06
    ovny
    -0.06
    .strict
    -0.06
    -find
    -0.06
     시스템
    -0.06
    POSITIVE LOGITS
    тра
    0.07
     pioneered
    0.07
    ++++++++++++++++++++++++++++++++
    0.07
    exion
    0.06
    ually
    0.06
    ńst
    0.06
    _notes
    0.06
     організ
    0.06
     vX
    0.06
    efs
    0.06
    Act Density 0.017%

    No Known Activations