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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns and related phrases indicating specificity

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

    it is this or that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apprendre
    -0.43
     ویکی‌پدی
    -0.42
    rungsseite
    -0.41
    ambién
    -0.39
    ungsver
    -0.38
    ISupport
    -0.38
     jump
    -0.36
     unknownFields
    -0.36
    问题
    -0.36
     deberían
    -0.35
    POSITIVE LOGITS
     thiệu
    0.45
    endphp
    0.45
    fastjson
    0.43
    AndEndTag
    0.43
    nextLine
    0.42
    writable
    0.42
    entiated
    0.42
    gbaar
    0.42
    UMBUS
    0.41
     المعيارى
    0.41
    Act Density 0.012%

    No Known Activations