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

    Neuronpedia

    INDEX
    Explanations

    the word "the" indicating definite articles or specific mentions in the text

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

    Immediately precedes nouns or adjectives

    np_acts-logits-general · gemini-2.0-flash

    the followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nemico
    -0.65
    OOTD
    -0.58
    Personensuche
    -0.55
     Gears
    -0.54
     descart
    -0.54
     nemici
    -0.51
    Zeneca
    -0.50
    mallow
    -0.49
     toege
    -0.49
    jgl
    -0.49
    POSITIVE LOGITS
     past
    0.71
     system
    0.68
     last
    0.67
     nation
    0.67
     timeval
    0.66
     other
    0.65
     former
    0.64
     most
    0.61
     main
    0.60
     GlobalKey
    0.60
    Act Density 0.133%

    No Known Activations