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

    Neuronpedia

    INDEX
    Explanations

    instances of functions and their annotations in code

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

    closing code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.98
     queſta
    -0.96
    uxxxx
    -0.95
    :✨
    -0.92
     betweenstory
    -0.91
    -0.90
     Infórmanos
    -0.89
    +#+#
    -0.88
     pinulongan
    -0.88
     nahilalakip
    -0.86
    POSITIVE LOGITS
    .
    0.57
    ?
    0.51
    :
    0.51
    t
    0.46
    0
    0.46
    1
    0.45
     
    0.45
      
    0.44
    2
    0.43
     is
    0.41
    Act Density 0.004%

    No Known Activations