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

    Neuronpedia

    INDEX
    Explanations

    phrases related to workplace interactions and communication

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

    Following a reporting verb

    np_acts-logits-general · gemini-2.0-flash

    reporting facts aloud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    preuve
    -0.61
     كومونز
    -0.60
    Espèce
    -0.57
     للاسماء
    -0.56
    تقاوى
    -0.48
    retudo
    -0.48
     Winaray
    -0.48
     تضيفلها
    -0.47
    findpost
    -0.47
    tivitas
    -0.47
    POSITIVE LOGITS
     kepada
    1.21
     auprès
    1.09
     aloud
    0.94
     publicly
    0.86
     unto
    0.80
     verbally
    0.78
    kepada
    0.75
     orally
    0.72
     loudly
    0.71
     στους
    0.70
    Act Density 0.447%

    No Known Activations