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

    Neuronpedia

    INDEX
    Explanations

    hyphens and numerical values within the text

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

    numeric values and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.87
    .*")]
    -0.71
     Administrativna
    -0.71
     betweenstory
    -0.71
    ConstraintMaker
    -0.66
    帖最后由
    -0.60
    transQ
    -0.58
    AsUp
    -0.57
    queryInterface
    -0.57
    NamedQueries
    -0.51
    POSITIVE LOGITS
    
    0.47
    ⓧ
    0.47
     rowspan
    0.47
    GroupLayout
    0.44
     laſſen
    0.42
    ​
    0.42
     steep
    0.42
     steeper
    0.42
    setcounter
    0.41
    MessageOf
    0.41
    Act Density 0.014%

    No Known Activations