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

    Neuronpedia

    INDEX
    Explanations

    code structure elements and methods for handling data

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

    Code or equations within text

    np_acts-logits-general · gemini-2.0-flash

    listing or respectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.81
     ComVisible
    -0.77
     MainAxisSize
    -0.69
     QtGui
    -0.69
    <?
    -0.67
     خارجية
    -0.66
     /\.
    -0.64
    
    -0.63
     utafitiHapana
    -0.61
    دانشنامهٔ
    -0.61
    POSITIVE LOGITS
    分別
    0.65
    分别
    0.63
     respectively
    0.60
     These
    0.56
    These
    0.54
     these
    0.53
    分别是
    0.53
    Everything
    0.53
    これらの
    0.52
     Everything
    0.52
    Act Density 0.202%

    No Known Activations