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

    Neuronpedia

    INDEX
    Explanations

    elements related to names and email addresses

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

    label followed by definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diwedd
    -0.63
     '\\;'
    -0.63
    ⓧ
    -0.57
     $_"
    -0.57
     setUsername
    -0.57
     AssemblyCompany
    -0.57
    OGND
    -0.55
    transQ
    -0.53
     ✭✭
    -0.52
    webElementGuid
    -0.52
    POSITIVE LOGITS
     is
    1.13
     lautet
    0.93
     ialah
    0.81
    คือ
    0.74
     là
    0.73
     adalah
    0.73
    的是
    0.67
     είναι
    0.60
     are
    0.58
    为
    0.57
    Act Density 0.217%

    No Known Activations