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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating options or alternatives

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

    whether or regardless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ✭✭
    -0.44
    WindowConstants
    -0.40
    Espèce
    -0.35
     betweenstory
    -0.35
    cookieParser
    -0.35
     henvisninger
    -0.35
     يتيمه
    -0.34
    astify
    -0.34
    ragalactic
    -0.33
    ähteet
    -0.32
    POSITIVE LOGITS
     للاسماء
    0.54
     kosmety
    0.46
    ंदीखरीदारी
    0.45
    oredCriteria
    0.45
    atever
    0.44
    υχ
    0.44
     tantangan
    0.44
    bibnamefont
    0.44
    jęt
    0.44
     challenging
    0.43
    Act Density 0.009%

    No Known Activations