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

    Neuronpedia

    INDEX
    Explanations

    communication methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     formulaire
    -0.07
    ظيف
    -0.07
    bam
    -0.06
    sparse
    -0.06
    ects
    -0.06
     Wak
    -0.06
    -mask
    -0.06
     بد
    -0.06
    esor
    -0.06
     svc
    -0.06
    POSITIVE LOGITS
    광고
    0.07
     Fireplace
    0.06
     acquaintance
    0.06
    ı
    0.06
    (area
    0.06
    >Delete
    0.06
    (sec
    0.06
    готов
    0.06
     менее
    0.06
    恵
    0.06
    Act Density 0.035%

    No Known Activations