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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structure markers

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

    end punctuation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vitt
    -0.50
    //});
    -0.49
    بوابة
    -0.46
    ?')
    -0.46
     cred
    -0.45
    Sev
    -0.45
     Import
    -0.45
     vul
    -0.44
     Fury
    -0.44
    axel
    -0.43
    POSITIVE LOGITS
     nonUne
    0.65
     mandatario
    0.62
    berdayakan
    0.48
     enamorado
    0.47
    endroit
    0.46
     comenzado
    0.46
    esterno
    0.46
    menina
    0.46
     hänen
    0.46
    colgante
    0.45
    Act Density 0.049%

    No Known Activations