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

    Neuronpedia

    INDEX
    Explanations

    text that contains disclaimers and informational warnings

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

    after negative polarity markers

    np_acts-logits-general · gemini-2.0-flash

    no advice disclaimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagext
    -0.63
    afficheront
    -0.58
    EDEFAULT
    -0.58
     CreateTagHelper
    -0.54
    heimer
    -0.54
     Yep
    -0.53
    ताब
    -0.51
    anskje
    -0.51
    Yup
    -0.51
    AddAttribute
    -0.51
    POSITIVE LOGITS
     linkovi
    0.64
     BoxDecoration
    0.61
     disclaimer
    0.58
    ِّف
    0.57
    
    0.54
     Euph
    0.54
    Personensuche
    0.53
    RectangleBorder
    0.52
     gonad
    0.51
    rawDesc
    0.47
    Act Density 0.261%

    No Known Activations