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

    Neuronpedia

    INDEX
    Explanations

    various forms of demonstrative pronouns and adjectives

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

    demonstrative pronouns in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.84
    oneofs
    -0.75
    Tikang
    -0.74
    Tembelea
    -0.73
    fromnode
    -0.73
     فريبيس
    -0.72
    fjspx
    -0.72
    Бахар
    -0.71
     صوتيه
    -0.70
     ویکی‌پدی
    -0.69
    POSITIVE LOGITS
     Dieses
    0.58
     Dieser
    0.55
     Этот
    0.52
    Dieses
    0.50
    This
    0.50
    Этот
    0.48
    Deze
    0.48
    These
    0.47
     Deze
    0.47
     Cette
    0.46
    Act Density 0.006%

    No Known Activations