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

    Neuronpedia

    INDEX
    Explanations

    ear

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     akin
    -0.07
     premises
    -0.07
    .imshow
    -0.07
    .pg
    -0.07
     Claude
    -0.07
    来访
    -0.06
    鬶
    -0.06
     Elm
    -0.06
    .Users
    -0.06
    炙
    -0.06
    POSITIVE LOGITS
    (&
    0.08
    ערה
    0.08
    ��
    0.08
    (bit
    0.07
    、“
    0.07
     design
    0.07
    =\
    0.07
    &#
    0.07
    <&
    0.07
    成为一个
    0.06
    Act Density 0.003%

    No Known Activations