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

    Neuronpedia

    INDEX
    Explanations

    references to components of a system or structure

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

    numbers three, four, or five

    np_acts-logits-general · gemini-2.0-flash

    numbers and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Thirty
    -0.71
    Sixty
    -0.63
    Twenty
    -0.62
    Fifteen
    -0.62
     Thirty
    -0.62
    thirty
    -0.60
     ribuan
    -0.60
    Forty
    -0.59
    ninth
    -0.59
     thirteenth
    -0.59
    POSITIVE LOGITS
     т
    0.86
     세
    0.76
     thr
    0.74
     triplet
    0.68
     three
    0.67
     tri
    0.62
     네
    0.62
     τ
    0.62
    三
    0.60
    viert
    0.60
    Act Density 0.371%

    No Known Activations