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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases that convey high quality and admiration

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

    respect organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    createClass
    -0.40
    CardHeader
    -0.37
    ochrom
    -0.37
    DockStyle
    -0.35
    ocyto
    -0.35
     Chwiliwch
    -0.34
     Keats
    -0.34
    Rip
    -0.33
    rite
    -0.33
    deelte
    -0.33
    POSITIVE LOGITS
    transQ
    0.86
     nonUne
    0.66
    دانشنامهٔ
    0.65
    RegressionTest
    0.64
    TypedDataSet
    0.61
    MessageTagHelper
    0.56
    تقاوى
    0.54
    发表于
    0.53
    AsUp
    0.52
     समीक्षाएं
    0.51
    Act Density 0.004%

    No Known Activations