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

    Neuronpedia

    INDEX
    Explanations

    references to a specific keypoint detection method

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

    Point or SuperPoint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.43
    Hochspringen
    -0.34
     Drama
    -0.33
    ))*
    -0.32
    usa
    -0.32
     FormsModule
    -0.31
    </thead>
    -0.31
    htm
    -0.31
    FormsModule
    -0.30
    endcsname
    -0.30
    POSITIVE LOGITS
     Point
    2.20
    Point
    2.16
     POINT
    1.65
    POINT
    1.42
     Pointe
    1.14
     Points
    1.12
    getPoint
    1.09
    point
    1.04
    Punto
    1.03
     Punto
    1.03
    Act Density 0.004%

    No Known Activations