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

    Neuronpedia

    INDEX
    Explanations

    historical and academic places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trillions
    0.71
     utilizzo
    0.69
     utilisez
    0.68
     বলিউড
    0.66
     onboarding
    0.65
     ransomware
    0.64
     bilhões
    0.64
     attualmente
    0.64
     использу
    0.64
     ನಿಮ್ಮ
    0.64
    POSITIVE LOGITS
     lectures
    0.65
     manuscripts
    0.63
     Polytechnic
    0.63
     Lectures
    0.60
     manuscript
    0.60
     pamphlets
    0.60
     Polytechn
    0.59
     lecture
    0.58
     tutors
    0.58
     literary
    0.58
    Act Density 0.070%

    No Known Activations