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

    Neuronpedia

    INDEX
    Explanations

    the word "patch" usually in a biological context

    oai_token-act-pair · gemini-2.0-flash

    patch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ものに
    -0.73
     
    -0.68
    я
    -0.67
    s
    -0.64
    <strong>
    -0.60
    e
    -0.59
    ment
    -0.54
    a
    -0.54
    ↵↵
    -0.52
    o
    -0.52
    POSITIVE LOGITS
     ModelExpression
    1.24
     intptr
    1.22
    IntoConstraints
    1.20
     дописавши
    1.19
     kasarigan
    1.19
     utafitiHapana
    1.18
     nakalista
    1.17
    twimg
    1.16
    AnchorStyles
    1.14
    XmlAccessType
    1.14
    Act Density 0.598%

    No Known Activations