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

    Neuronpedia

    INDEX
    Explanations

    references to definitions and explanations

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

    legal citations and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Whilst
    -0.71
    Whilst
    -0.70
     whilst
    -0.66
     Amongst
    -0.66
     amongst
    -0.63
     onwards
    -0.61
     firstly
    -0.58
     spoilt
    -0.58
     artefacts
    -0.55
     Firstly
    -0.54
    POSITIVE LOGITS
     dévelo
    0.60
     plufieurs
    0.59
     surla
    0.58
     Infór
    0.56
     leçon
    0.56
    Tikang
    0.55
     lizenzfreies
    0.55
    iowa
    0.53
     amitié
    0.52
     eſſ
    0.52
    Act Density 0.011%

    No Known Activations