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

    Neuronpedia

    INDEX
    Explanations

    reality and environment states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Millionen
    0.61
    िटेशन
    0.61
     verschiedene
    0.60
    olphe
    0.60
    quen
    0.58
    ആ
    0.58
    িগুণ
    0.57
     Länge
    0.57
    റ്റം
    0.57
    替え
    0.56
    POSITIVE LOGITS
     landscape
    2.14
     reality
    1.78
    landscape
    1.66
     realities
    1.59
     Landscape
    1.57
     landscapes
    1.52
     paysage
    1.47
     outlook
    1.43
     environment
    1.39
    Landscape
    1.39
    Act Density 0.656%

    No Known Activations