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

    Neuronpedia

    INDEX
    Explanations

    scientific/medical abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vol
    -0.07
     Fixture
    -0.07
    .ModelAdmin
    -0.07
    YLON
    -0.07
     attractions
    -0.07
    	logging
    -0.07
     Nath
    -0.07
    Roman
    -0.06
     Homo
    -0.06
    edList
    -0.06
    POSITIVE LOGITS
    hue
    0.07
    Schedulers
    0.07
    騙
    0.07
    _on
    0.07
    电工
    0.07
     Eisenhower
    0.06
    炱
    0.06
    痘
    0.06
    )row
    0.06
    꾀
    0.06
    Act Density 0.119%

    No Known Activations