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

    Neuronpedia

    INDEX
    Explanations

    academic articles and the various ways they present and analyze research topics

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

    summarizing, outlining, or discussing

    np_acts-logits-general · gemini-2.0-flash

    discussing, summarizing, explaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.87
    CloseOperation
    -0.79
     AssemblyVersion
    -0.70
     Shakspeare
    -0.65
     InputDecoration
    -0.62
    photobucket
    -0.61
    CAPTION
    -0.61
     ThemeData
    -0.61
     ComVisible
    -0.61
    ConstraintMaker
    -0.61
    POSITIVE LOGITS
     how
    1.67
     why
    1.35
     ways
    1.24
    how
    1.07
     what
    1.05
     cómo
    1.00
     reasons
    1.00
     some
    0.99
     waarom
    0.96
    why
    0.96
    Act Density 0.658%

    No Known Activations