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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    errat
    -0.07
    logout
    -0.07
     gens
    -0.06
     Méd
    -0.06
     dementia
    -0.06
    edla
    -0.06
     án
    -0.06
    ασία
    -0.06
     Covent
    -0.06
     suppl
    -0.06
    POSITIVE LOGITS
    ルの
    0.06
    	Id
    0.06
     ToString
    0.06
    aying
    0.06
    :*
    0.06
    _CITY
    0.06
    ุมภาพ
    0.06
    IOR
    0.06
    	de
    0.06
    ΙΔ
    0.05
    Act Density 0.003%

    No Known Activations