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

    Neuronpedia

    INDEX
    Explanations

    discussions or references to overall evaluations or conclusions

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

    overall [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.63
     CURIAM
    -0.63
     lenker
    -0.59
     autorytatywna
    -0.54
    сылкі
    -0.54
    ագրություններ
    -0.54
     հղումներ
    -0.54
    üyada
    -0.54
     بيها
    -0.52
    منابع
    -0.50
    POSITIVE LOGITS
     overall
    0.58
     Gesamt
    0.49
    全体の
    0.48
    intera
    0.47
     Gesam
    0.46
     surrounding
    0.46
     entire
    0.44
    整體
    0.44
     general
    0.43
     prevailing
    0.41
    Act Density 0.027%

    No Known Activations