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

    Neuronpedia

    INDEX
    Explanations

    traffic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enrichment
    -0.08
     bounding
    -0.07
    $$$
    -0.07
     Seasons
    -0.07
    浪
    -0.06
     valeurs
    -0.06
    تمبر
    -0.06
     callable
    -0.06
    
    -0.06
     collisions
    -0.06
    POSITIVE LOGITS
     Revolutionary
    0.07
    Verify
    0.06
    edes
    0.06
    _don
    0.06
     이루
    0.06
     vui
    0.06
     ауд
    0.06
     TRAN
    0.06
    文章
    0.06
     Trev
    0.05
    Act Density 0.009%

    No Known Activations