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

    Neuronpedia

    INDEX
    Explanations

    segments of code or programming constructs

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

    programming definitions and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italij
    -0.63
     Infór
    -0.61
     للمعارف
    -0.58
     autorytatywna
    -0.57
     CreateTagHelper
    -0.57
     ainfi
    -0.57
     plufieurs
    -0.57
     mijne
    -0.56
     beginnetje
    -0.56
    Specifiche
    -0.56
    POSITIVE LOGITS
    nodoc
    0.54
    omba
    0.49
    oka
    0.48
    ⎥
    0.48
    thoven
    0.48
     rung
    0.47
     ս
    0.47
    #![
    0.46
     Dig
    0.46
    loo
    0.46
    Act Density 0.007%

    No Known Activations