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

    Neuronpedia

    INDEX
    Explanations

    tracking health information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blessed
    -0.07
     ud
    -0.06
     퍼
    -0.06
    рес
    -0.06
    ंध
    -0.06
    �
    -0.06
     shelter
    -0.06
     saja
    -0.06
    neum
    -0.06
    views
    -0.06
    POSITIVE LOGITS
     �
    0.06
     إذ
    0.06
    [test
    0.06
    reds
    0.06
    (ll
    0.06
     آش
    0.06
    Holy
    0.06
    */
↵
    0.06
    cop
    0.06
     gigg
    0.06
    Act Density 0.019%

    No Known Activations