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

    Neuronpedia

    INDEX
    Explanations

    instances of high activation patterns in data analysis

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

    scientific and foreign terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.63
    DockStyle
    -0.60
     defStyle
    -0.57
    Personendaten
    -0.56
    +#+
    -0.51
     [*]
    -0.49
    VersionUID
    -0.47
     للاسماء
    -0.46
     nakalista
    -0.43
     defStyleAttr
    -0.43
    POSITIVE LOGITS
     türlü
    0.51
     caseros
    0.49
     nahilalakip
    0.49
     domestiques
    0.47
    তথ্যসূত্র
    0.46
    disfraz
    0.46
    Schwer
    0.45
     scientifiques
    0.44
     vraie
    0.44
     scientifique
    0.44
    Act Density 0.481%

    No Known Activations