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

    Neuronpedia

    INDEX
    Explanations

    punctuation and its variations across different contexts

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

    end of sentence or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.95
    Diweddarwch
    -0.86
     المعيارى
    -0.81
     surla
    -0.79
    GEBURTSDATUM
    -0.75
    AISSEE
    -0.75
     kasarigan
    -0.73
    󠁣
    -0.72
    хьтан
    -0.70
     Meksiku
    -0.68
    POSITIVE LOGITS
     licha
    0.27
     nostru
    0.24
     Sucher
    0.23
     اختیار
    0.23
     lucru
    0.23
     technische
    0.22
    rettet
    0.22
    +:+
    0.21
     precisely
    0.21
     argint
    0.21
    Act Density 0.007%

    No Known Activations