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

    Neuronpedia

    INDEX
    Explanations

    elements related to image and figure captions in code

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

    images and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -1.20
    transQ
    -0.97
    AddTagHelper
    -0.97
    <unused41>
    -0.91
    <unused68>
    -0.91
    <unused52>
    -0.91
    <unused74>
    -0.91
    ſſung
    -0.91
    <unused3>
    -0.91
    <unused8>
    -0.91
    POSITIVE LOGITS
    P
    0.37
     photo
    0.34
    img
    0.33
    photo
    0.33
    Photo
    0.33
    a
    0.32
    image
    0.31
    Image
    0.31
     images
    0.31
    images
    0.30
    Act Density 0.008%

    No Known Activations