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

    Neuronpedia

    INDEX
    Explanations

    HTML anchor tags or links within the content

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

    HTML <a> tag

    np_acts-logits-general · gemini-2.0-flash

    a href

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '><
    -0.75
    ;"><
    -0.74
    "><
    -0.71
    ="#"><
    -0.69
    '<
    -0.69
     `<
    -0.67
    :<
    -0.67
    ;<
    -0.65
    )<
    -0.65
    *<
    -0.65
    POSITIVE LOGITS
     href
    0.85
     target
    0.54
    herself
    0.51
    href
    0.48
    gway
    0.47
     Crowe
    0.47
    corr
    0.46
     TARGET
    0.45
    Href
    0.45
    IERS
    0.45
    Act Density 0.163%

    No Known Activations