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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrayList
    -0.08
     affair
    -0.07
    	sd
    -0.06
    ployment
    -0.06
     decimal
    -0.06
     qued
    -0.06
     positioning
    -0.06
     OSD
    -0.06
     Hospitality
    -0.06
     бел
    -0.06
    POSITIVE LOGITS
     kvinde
    0.07
     рекомендуется
    0.06
    λή
    0.06
    _subtitle
    0.06
    发
    0.06
     inflate
    0.06
    issant
    0.06
     Stephan
    0.06
    .ReadAll
    0.06
    _minute
    0.06
    Act Density 0.033%

    No Known Activations