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

    Neuronpedia

    INDEX
    Explanations

    statements and questions about expectations and outcomes

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

    Personal opinions or beliefs

    np_acts-logits-general · gemini-2.0-flash

    past thoughts or assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -0.93
     BoxDecoration
    -0.90
     дописавши
    -0.79
     pleaſure
    -0.79
    MessageTagHelper
    -0.78
    contentLoaded
    -0.78
     ſtate
    -0.77
     spéciaux
    -0.76
     fubject
    -0.75
     NSCoder
    -0.72
    POSITIVE LOGITS
     imagined
    0.76
     initially
    0.69
     anticipated
    0.66
     imagine
    0.66
     imagines
    0.61
    想象
    0.60
     imagining
    0.57
     thought
    0.57
     perhaps
    0.56
     originally
    0.55
    Act Density 0.135%

    No Known Activations