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

    Neuronpedia

    INDEX
    Explanations

    numbers or amounts

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is spot numeric “n-of-m” threshold expressions (e.g. “2-of-3,” “7 of 10”) typically used to specify how many signatures or conditions are required.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical terms and concepts related to blockchain technology.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Jeans
    -0.07
    -tools
    -0.06
     červ
    -0.06
     Colt
    -0.06
     -↵↵
    -0.06
    をつ
    -0.06
     ten
    -0.06
     chained
    -0.06
    Borders
    -0.06
    创建
    -0.06
    POSITIVE LOGITS
    mis
    0.06
    getVar
    0.06
    يش
    0.06
    แบบ
    0.06
    Ext
    0.06
     Rid
    0.06
    praak
    0.06
     aktar
    0.06
    Term
    0.06
     nag
    0.06
    Act Density 0.056%

    No Known Activations