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

    Neuronpedia

    INDEX
    Explanations

    references to calculations and text-related components in programming or markup languages

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

    text styling code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ['./
    -0.44
    Personensuche
    -0.44
    /**
    -0.42
    flink
    -0.41
    ########.
    -0.41
    expandindo
    -0.40
     Blockly
    -0.40
     Kommission
    -0.38
    </tfoot>
    -0.37
    WebServlet
    -0.37
    POSITIVE LOGITS
    Text
    0.77
    createTextNode
    0.76
     Text
    0.73
    fillText
    0.62
     JLabel
    0.60
     BoxDecoration
    0.60
    FontOfSize
    0.57
    setText
    0.57
     imageNamed
    0.57
     text
    0.55
    Act Density 0.001%

    No Known Activations