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

    Neuronpedia

    INDEX
    Explanations

    significant whitespace or indentation in code

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

    code snippets and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elemField
    -0.55
    principalColumn
    -0.55
    COUVER
    -0.54
    ReusableCell
    -0.53
     Paglinawan
    -0.52
     informée
    -0.51
     تضيفلها
    -0.50
    tdessen
    -0.49
     MainAxisSize
    -0.49
    alala
    -0.48
    POSITIVE LOGITS
     chain
    0.42
     function
    0.40
     his
    0.40
     build
    0.39
     energy
    0.38
     opening
    0.38
     using
    0.38
     reach
    0.38
     training
    0.36
     window
    0.36
    Act Density 0.008%

    No Known Activations