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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ™s
    -0.09
    Scenes
    -0.08
    vamos
    -0.08
    /time
    -0.08
    leri
    -0.08
     urgente
    -0.08
    Cr
    -0.08
     ఉంది
    -0.08
    lerden
    -0.08
    ింద
    -0.08
    POSITIVE LOGITS
     ktoré
    0.10
     שונות
    0.10
     themselves
    0.10
     связанные
    0.09
     które
    0.09
     שונים
    0.09
     eraill
    0.09
     économiques
    0.09
     אחרות
    0.09
     arasında
    0.09
    Act Density 0.223%

    No Known Activations