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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing exclusivity or uniqueness

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

    not only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.40
    getMenuInflater
    -0.39
    เห
    -0.38
    CHOICES
    -0.35
     ویکی‌پدی
    -0.35
    rceil
    -0.34
    nEnter
    -0.34
    bibinfo
    -0.34
    Condol
    -0.34
    Embeddable
    -0.33
    POSITIVE LOGITS
     nejen
    0.72
    不仅
    0.64
    不但
    0.62
    owohl
    0.61
    不僅
    0.60
    enumi
    0.58
    autant
    0.58
    不仅仅
    0.57
    GOTREF
    0.56
    jména
    0.56
    Act Density 0.006%

    No Known Activations