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

    Neuronpedia

    INDEX
    Explanations

    commands or questions that begin with "do."

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

    do not, does not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -0.58
    :✨
    -0.58
     autorytatywna
    -0.57
    ⓧ
    -0.54
    AccessorTable
    -0.54
     WebDriverWait
    -0.54
    出版年
    -0.53
     Majefty
    -0.53
    ScopeManager
    -0.52
    ьаж
    -0.51
    POSITIVE LOGITS
    nest
    0.41
     noDo
    0.41
    liq
    0.36
    riet
    0.35
    üte
    0.34
    ည်
    0.34
     gsm
    0.33
     跳转至
    0.33
     LIG
    0.33
    lic
    0.33
    Act Density 0.184%

    No Known Activations