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

    Neuronpedia

    INDEX
    Explanations

    complexities and confusions in explanations or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    confusing and complicated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.82
    RenderAtEndOf
    -0.54
    RotationOrder
    -0.54
    .*")]
    -0.48
    StoryboardSegue
    -0.46
    Personendaten
    -0.45
    AnimationsModule
    -0.43
    GRANTED
    -0.42
     uska
    -0.42
    enumii
    -0.41
    POSITIVE LOGITS
     confusing
    0.66
     perplexing
    0.60
     confused
    0.53
     confuse
    0.50
     confuses
    0.50
     erratic
    0.49
     puzzling
    0.49
     strangest
    0.48
     confounding
    0.46
     confusion
    0.45
    Act Density 0.078%

    No Known Activations