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

    Neuronpedia

    INDEX
    Explanations

    words that indicate various forms of societal organization, structures, and classifications

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

    followed by a period or comma

    np_acts-logits-general · gemini-2.0-flash

    concepts and subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     déput
    -0.78
     stället
    -0.77
    ็จ
    -0.75
     kasarigan
    -0.74
    ViewImports
    -0.74
     الحره
    -0.74
    addGap
    -0.73
    AnimationsModule
    -0.73
     CGRectMake
    -0.73
    ContentAsync
    -0.70
    POSITIVE LOGITS
    ,
    0.76
    .
    0.66
     and
    0.61
    ,”
    0.54
    :
    0.53
    …~
    0.53
    ;
    0.52
     as
    0.52
     or
    0.51
     is
    0.51
    Act Density 0.253%

    No Known Activations