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

    Neuronpedia

    INDEX
    Explanations

    desires

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gebied
    -0.08
    gain
    -0.07
    -standing
    -0.07
     aanleiding
    -0.07
     ultras
    -0.07
    ways
    -0.07
     Steele
    -0.07
    Prov
    -0.07
     airing
    -0.07
    IMPORT
    -0.07
    POSITIVE LOGITS
     imaginable
    0.11
     تقريب
    0.10
     Anlage
    0.09
     sauf
    0.09
     необходимые
    0.09
     necesarias
    0.09
     الأساسية
    0.09
     πραγμα
    0.08
     moderne
    0.08
     nécessaires
    0.08
    Act Density 0.143%

    No Known Activations