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

    Neuronpedia

    INDEX
    Explanations

    elements related to argumentation and reasoning

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

    ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Дереккөздер
    -0.50
    хьтан
    -0.49
     ligiloj
    -0.49
    Sklici
    -0.48
    Jegyzetek
    -0.47
    Ƚ
    -0.47
    лтамалар
    -0.45
     BIBSYS
    -0.44
    liesslich
    -0.44
    ➌
    -0.43
    POSITIVE LOGITS
    AndEndTag
    0.52
     himself
    0.42
     незавершена
    0.42
    انجليز
    0.41
    saraba
    0.38
    awtextra
    0.35
    ंदीखरीदारी
    0.35
    disco
    0.33
     niya
    0.33
    himself
    0.33
    Act Density 0.063%

    No Known Activations