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

    Neuronpedia

    INDEX
    Explanations

    references to leadership roles or positions of authority

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

    "head" followed by various prepositions or titles

    np_acts-logits-general · gemini-2.0-flash

    head followed by noun or adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disponibilités
    -0.82
    momix
    -0.81
    ✨:
    -0.79
    rungsseite
    -0.79
     nahilalakip
    -0.77
    PRNewswire
    -0.72
    ]]);
    -0.72
    <?
    -0.70
     مشين
    -0.68
    UNITY
    -0.67
    POSITIVE LOGITS
     HEAD
    1.40
     heads
    1.37
     Head
    1.36
     head
    1.36
    Head
    1.29
     Heads
    1.25
    head
    1.21
     Kopf
    1.16
    HEAD
    1.14
    heads
    1.13
    Act Density 0.094%

    No Known Activations