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

    Neuronpedia

    INDEX
    Explanations

    terms indicating similarity or comparison

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

    preceding "to" or ending in "ly"

    np_acts-logits-general · gemini-2.0-flash

    similar to adjectives or adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.67
    expandindo
    -0.57
    ModelAdmin
    -0.54
    IGraphics
    -0.51
     createSprite
    -0.48
    -0.48
     ReactDOM
    -0.48
    stateProvider
    -0.47
    __':
    -0.47
    Билгалдахарш
    -0.46
    POSITIVE LOGITS
    ily
    0.58
     sytu
    0.42
    ibatis
    0.41
     kinds
    0.41
    SPATH
    0.40
     nôtre
    0.38
     enough
    0.38
    슷
    0.37
     situasi
    0.37
     sized
    0.37
    Act Density 0.228%

    No Known Activations