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

    Neuronpedia

    INDEX
    Explanations

    words and phrases expressing logical relationships (e.g. "of the", "in the", "that water").

    oai_token-act-pair · gemini-2.0-flash

    locations within a house

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    הערות
    -0.50
     fotográfico
    -0.45
    cedor
    -0.44
    Mikro
    -0.44
     pointers
    -0.43
     arvio
    -0.42
     cryptography
    -0.42
    board
    -0.41
    Upper
    -0.41
     sprink
    -0.41
    POSITIVE LOGITS
    WebVitals
    0.88
    parsedMessage
    0.78
    SharedDtor
    0.65
    ollectionView
    0.65
    webElementXpaths
    0.65
     onBind
    0.63
     pulumi
    0.63
    RenderAtEndOf
    0.63
    PreferredItem
    0.63
    resave
    0.61
    Act Density 2.822%

    No Known Activations