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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical operations and calculations

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

    math questions about divisibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    smithy
    -0.39
     pusi
    -0.38
    ┑
    -0.37
     BUL
    -0.34
     getLayout
    -0.34
     triumph
    -0.34
    ┓
    -0.33
    勝
    -0.33
     proto
    -0.33
    urbo
    -0.33
    POSITIVE LOGITS
    :✨
    0.69
    principalColumn
    0.52
     aapt
    0.52
    VersionUID
    0.50
     MainAxisSize
    0.49
    IndentedString
    0.46
    GEBURTS
    0.46
     Numerade
    0.46
     gyhoeddwyd
    0.46
    ipelago
    0.45
    Act Density 0.024%

    No Known Activations