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

    Neuronpedia

    INDEX
    Explanations

    URLs and references to online resources

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

    URLs and academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.94
    AndEndTag
    -0.64
     виправивши
    -0.63
    ➟
    -0.62
     propOrder
    -0.61
     للمعارف
    -0.61
     defaultstate
    -0.60
    تقاوى
    -0.56
    WebVitals
    -0.56
     protoimpl
    -0.55
    POSITIVE LOGITS
     websites
    0.40
     bomberos
    0.38
     www
    0.36
     website
    0.35
    AspNet
    0.35
    Rusia
    0.33
     información
    0.33
     Internet
    0.33
    gov
    0.32
     bilgi
    0.32
    Act Density 0.003%

    No Known Activations