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

    Neuronpedia

    INDEX
    Explanations

    functional requirements ISO 26262

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solitons
    0.48
     ninja
    0.46
     mortgages
    0.44
     mario
    0.42
     demok
    0.41
     slimming
    0.41
     multiplayer
    0.40
     skyscrapers
    0.40
     rivals
    0.40
     rubble
    0.40
    POSITIVE LOGITS
    cknow
    0.39
    质量
    0.39
    :
    0.39
    2
    0.38
     Principles
    0.38
     Curriculum
    0.38
    4
    0.38
     Assessment
    0.38
     pertinente
    0.37
    OC
    0.37
    Act Density 0.041%

    No Known Activations