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

    Neuronpedia

    INDEX
    Explanations

    <table

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IDb
    -0.08
     ingredient
    -0.08
    amaño
    -0.07
     внут
    -0.07
    为导向
    -0.07
    .jd
    -0.07
    湘潭
    -0.07
    conut
    -0.07
    iculture
    -0.07
    荁
    -0.07
    POSITIVE LOGITS
    ORE
    0.07
     foo
    0.07
     arttır
    0.07
    مالك
    0.07
     _:
    0.07
    fld
    0.07
    ARK
    0.07
    *:
    0.07
    ,,,,
    0.06
     />}↵
    0.06
    Act Density 0.002%

    No Known Activations