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

    Neuronpedia

    INDEX
    Explanations

    Cobb chooses reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dopo
    0.48
     με
    0.46
     Hepatitis
    0.46
     Internet
    0.45
     Util
    0.45
     Equip
    0.44
     Audi
    0.44
     Daarna
    0.44
     Boca
    0.44
     Memory
    0.44
    POSITIVE LOGITS
    安定
    0.48
     unwillingness
    0.48
     accountability
    0.47
    ህል
    0.46
     willingness
    0.46
    RAchievement
    0.45
     genial
    0.45
     политики
    0.45
    和谐
    0.44
     мотива
    0.44
    Act Density 0.006%

    No Known Activations