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

    Neuronpedia

    INDEX
    Explanations

    URLs or links, specifically those starting with "https"

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

    URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    躇
    -0.48
    subpackage
    -0.47
    amodel
    -0.42
    orteur
    -0.41
    andReturn
    -0.39
    /*---
    -0.39
     endblock
    -0.39
    scalatest
    -0.38
     actionMode
    -0.38
     vorbehalten
    -0.37
    POSITIVE LOGITS
    https
    2.80
     https
    2.47
    ttps
    1.81
    http
    1.78
    Https
    1.68
     http
    1.66
     HTTPS
    1.59
    HTTPS
    1.45
     Http
    1.10
    Http
    1.05
    Act Density 0.010%

    No Known Activations