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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the presence of conversations or dialogues in narratives

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

    Prepositions indicating location or movement

    np_acts-logits-general · gemini-2.0-flash

    location or direction inside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.56
    tahui
    -0.49
    Outside
    -0.47
     VEGAS
    -0.46
    picasso
    -0.45
    astify
    -0.45
    styleable
    -0.45
     perifer
    -0.44
    IGraphics
    -0.44
    ImageContext
    -0.43
    POSITIVE LOGITS
     inside
    1.05
     Inside
    1.03
     indoors
    0.99
    Inside
    0.99
    inside
    0.95
     indoor
    0.90
     interior
    0.88
     INSIDE
    0.85
     interiors
    0.84
    indoor
    0.81
    Act Density 0.184%

    No Known Activations