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

    Neuronpedia

    INDEX
    Explanations

    words indicating inclusivity or a sense of community

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

    French, Japanese, and Chinese words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MIDDLEWARE
    -0.55
    ffè
    -0.47
    asarray
    -0.47
    EDEFAULT
    -0.45
    fjspx
    -0.45
    NICE
    -0.45
     setPrice
    -0.45
     Verf
    -0.44
    liert
    -0.43
    UnusedPrivate
    -0.43
    POSITIVE LOGITS
    跟
    0.54
    どう
    0.54
    どうか
    0.54
    よろしくお願いします
    0.53
    ต้อง
    0.52
    brinco
    0.51
    temuan
    0.50
     跟
    0.50
    宜しくお願い
    0.48
    ご馳走
    0.48
    Act Density 0.003%

    No Known Activations