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

    Neuronpedia

    INDEX
    Explanations

    instructions related to formatting text in a code or document editor

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

    Follows punctuation in code or lists

    np_acts-logits-general · gemini-2.0-flash

    select and choose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发表于
    -0.72
    Portale
    -0.71
    MeasureSpec
    -0.61
     estimés
    -0.55
     smtplib
    -0.53
    itemBuilder
    -0.52
    ApiRequest
    -0.51
    horesis
    -0.50
    BeginInit
    -0.49
     "{\"
    -0.49
    POSITIVE LOGITS
     selections
    0.68
     preview
    0.62
    inspection
    0.61
    selecting
    0.60
     selection
    0.59
     선택
    0.59
     selecting
    0.59
     unwanted
    0.58
     selected
    0.57
     Selecting
    0.56
    Act Density 0.373%

    No Known Activations