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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     camar
    -0.06
    켜
    -0.06
    措
    -0.06
     D
    -0.06
    Hur
    -0.06
     anecd
    -0.06
    ується
    -0.06
     تور
    -0.06
     CentOS
    -0.06
     firestore
    -0.06
    POSITIVE LOGITS
     труб
    0.07
    ="↵
    0.07
    (moment
    0.06
     Background
    0.06
    (plot
    0.06
    (internal
    0.06
    (bean
    0.06
     投稿日
    0.06
     rewritten
    0.06
     relate
    0.06
    Act Density 0.016%

    No Known Activations