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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Merry
    -0.07
     TAX
    -0.07
    Prime
    -0.07
    .xlabel
    -0.07
    Capital
    -0.07
     closely
    -0.06
     plural
    -0.06
     Ud
    -0.06
     WHILE
    -0.06
    309
    -0.06
    POSITIVE LOGITS
    /".$
    0.06
     İngiliz
    0.06
    овід
    0.06
    ırak
    0.06
    /*↵
    0.06
    (ii
    0.06
     sees
    0.06
    užel
    0.06
    eği
    0.06
     disb
    0.06
    Act Density 0.048%

    No Known Activations