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

    Neuronpedia

    INDEX
    Explanations

    discussions about natural processes or phenomena and their implications

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

    suggesting something is expected or obvious

    np_acts-logits-general · gemini-2.0-flash

    natural or logical progression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.63
     totiž
    -0.54
    RenderAtEndOf
    -0.51
     nemlig
    -0.51
    flashdata
    -0.51
     архивлан
    -0.50
    HasAnnotation
    -0.50
     vorbei
    -0.50
     nämlich
    -0.48
    endpush
    -0.48
    POSITIVE LOGITS
     naturally
    1.97
     natural
    1.90
     logical
    1.83
    natural
    1.70
    naturally
    1.70
     Naturally
    1.63
    Natural
    1.61
     logically
    1.60
     Natural
    1.59
     obvious
    1.58
    Act Density 0.419%

    No Known Activations