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

    Neuronpedia

    INDEX
    Explanations

    the word "First" used to denote the beginning of a list or sequence

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

    introducing the word first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    YJ
    -0.35
     MCC
    -0.35
    lyt
    -0.34
    mot
    -0.32
    toid
    -0.32
     Fer
    -0.32
    jiny
    -0.32
    isateur
    -0.32
     चुनें
    -0.31
     tuy
    -0.31
    POSITIVE LOGITS
    出版年
    0.81
    SequentialGroup
    0.71
     AssemblyCulture
    0.63
     esternos
    0.61
    RequestMapping
    0.59
    boneca
    0.59
     Wikiseite
    0.58
    Primeiro
    0.58
    addLast
    0.57
    GIVEREF
    0.57
    Act Density 0.026%

    No Known Activations