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

    Neuronpedia

    INDEX
    Explanations

    news/event reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Species
    -0.07
    (all
    -0.07
    cou
    -0.06
     Pakistan
    -0.06
     Authors
    -0.06
    ↵    ↵    ↵
    -0.06
    Productos
    -0.06
    :
↵
↵
    -0.06
    	cal
    -0.06
     Belize
    -0.06
    POSITIVE LOGITS
    qli
    0.06
     uğra
    0.06
    iphertext
    0.06
    _TMP
    0.06
     توم
    0.06
    жа
    0.06
    /filepath
    0.06
    飯
    0.06
    ATIO
    0.06
     ups
    0.06
    Act Density 0.054%

    No Known Activations