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

    Neuronpedia

    INDEX
    Explanations

    patterns and conditional phrases related to decision-making and preference

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    technical code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зю
    -0.58
    Externé
    -0.56
     đăng
    -0.54
     bangun
    -0.53
    XtraGrid
    -0.53
    randi
    -0.53
    것은
    -0.52
    EqualsAnd
    -0.52
     )$
    -0.51
     nenhum
    -0.51
    POSITIVE LOGITS
    XmlRootElement
    0.66
    setVerticalGroup
    0.63
    MessageTagHelper
    0.60
    XmlEnum
    0.59
    OGND
    0.56
     NSCoder
    0.54
    SourceChecksum
    0.52
    Personendaten
    0.52
     initComponents
    0.51
     Bahkan
    0.50
    Act Density 0.006%

    No Known Activations