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

    Neuronpedia

    INDEX
    Explanations

    references to awards and honors received

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

    awards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.49
     Sauer
    -0.49
     Kompon
    -0.46
    NUMX
    -0.45
    FormTagHelper
    -0.45
     EconPapers
    -0.45
     sinks
    -0.44
     članak
    -0.43
    inière
    -0.42
    ioutil
    -0.42
    POSITIVE LOGITS
     awards
    0.88
    Auszeichnungen
    0.79
     récompenses
    0.79
    Awards
    0.75
    awards
    0.74
     award
    0.72
     Awards
    0.69
     récompense
    0.69
     penghargaan
    0.66
    colades
    0.65
    Act Density 0.021%

    No Known Activations