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

    Neuronpedia

    INDEX
    Explanations

    Code commands and arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alan
    -0.08
    alami
    -0.08
    øl
    -0.08
     Valentine
    -0.08
    raj
    -0.08
    adar
    -0.08
     goats
    -0.07
     kung
    -0.07
    centration
    -0.07
     liter
    -0.07
    POSITIVE LOGITS
     команд
    0.08
    ева
    0.08
     authorization
    0.08
    ابقة
    0.08
    كه
    0.07
    یار
    0.07
     exhibition
    0.07
     ote
    0.07
    elfeld
    0.07
    -ẹrọ
    0.07
    Act Density 0.000%

    No Known Activations