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

    Neuronpedia

    INDEX
    Explanations

    stop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Declaration
    -0.08
    \Desktop
    -0.07
     nouns
    -0.07
    02
    -0.07
     Object
    -0.07
    孙
    -0.06
    01
    -0.06
     Plans
    -0.06
     Hale
    -0.06
    近
    -0.06
    POSITIVE LOGITS
     stopped
    0.08
     الاح
    0.07
    ザー
    0.06
    推荐
    0.06
    stopped
    0.06
    مع
    0.06
     Mister
    0.06
    437
    0.06
    .HashSet
    0.06
     ราค
    0.06
    Act Density 0.013%

    No Known Activations