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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

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

    <start_of_turn>user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageState
    -0.50
     चीज़ों
    -0.50
    FlatAppearance
    -0.47
     lendemain
    -0.43
     snippetHide
    -0.42
    ReusableCell
    -0.41
    addGap
    -0.40
    цездатний
    -0.40
    UrlResolution
    -0.40
    JspWriter
    -0.38
    POSITIVE LOGITS
    ⤹
    0.57
     Kite
    0.51
     AMI
    0.50
    kkit
    0.48
    LayoutConstraint
    0.48
    mande
    0.48
    IUrlHelper
    0.47
     Plot
    0.47
    houette
    0.47
     monsoon
    0.47
    Act Density 0.000%

    No Known Activations