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

    Neuronpedia

    INDEX
    Explanations

    ug

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Si
    -0.07
    723
    -0.07
     "/"↵
    -0.07
    Si
    -0.06
     Comments
    -0.06
     insulting
    -0.06
    Ark
    -0.06
    -0.06
     Ala
    -0.06
    	video
    -0.06
    POSITIVE LOGITS
    Quality
    0.07
     وأن
    0.06
    ="'.
    0.06
     dép
    0.06
    uação
    0.06
    科学
    0.06
    $client
    0.06
    uja
    0.06
    ję
    0.06
    (SQLException
    0.06
    Act Density 0.001%

    No Known Activations