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

    Neuronpedia

    INDEX
    Explanations

    terms indicating significance or magnitude

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

    expressing scale or significance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    actionMode
    -0.53
    InstrumentedTest
    -0.46
     "..\..\
    -0.45
     medarbe
    -0.43
    ագրություններ
    -0.43
     "..\..\..\
    -0.42
    acidade
    -0.40
     aprendizagem
    -0.40
     organisée
    -0.40
     skjø
    -0.40
    POSITIVE LOGITS
     important
    0.76
    huge
    0.70
    important
    0.68
     huge
    0.66
    Huge
    0.65
     HUGE
    0.64
     Important
    0.63
     importance
    0.63
     importants
    0.62
     Huge
    0.60
    Act Density 0.014%

    No Known Activations