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

    Neuronpedia

    INDEX
    Explanations

    URLs, particularly those starting with "https://"

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

    URLs, often to software development sites

    np_acts-logits-general · gemini-2.0-flash

    links to github and online services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orszá
    -0.59
    DotNetBar
    -0.57
     ModelAndView
    -0.56
    langsung
    -0.55
    Jeografia
    -0.53
     ddelweddau
    -0.53
    PhysRevLett
    -0.53
    PreferredItem
    -0.51
     فريبيس
    -0.50
    tagext
    -0.49
    POSITIVE LOGITS
    github
    1.15
     github
    0.74
    medium
    0.64
    doi
    0.62
    ibb
    0.59
    RectangleBorder
    0.59
    gitlab
    0.58
    gist
    0.56
    drive
    0.55
    FailureListener
    0.55
    Act Density 0.075%

    No Known Activations