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

    Neuronpedia

    INDEX
    Explanations

    patterns in code import statements

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

    "import com" statements

    np_acts-logits-general · gemini-2.0-flash

    import com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Verk
    -0.58
     Arctic
    -0.58
    higer
    -0.56
    zieher
    -0.55
    principalTable
    -0.53
     auffi
    -0.52
    ngdoc
    -0.51
     forgetting
    -0.50
     forgets
    -0.50
     LXXX
    -0.50
    POSITIVE LOGITS
     com
    0.96
    com
    0.84
    fromnode
    0.66
    errHandler
    0.65
     Com
    0.59
    Tracce
    0.56
     compressor
    0.55
    Com
    0.54
     TextInputType
    0.54
     RequestMethod
    0.53
    Act Density 0.022%

    No Known Activations