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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their titles or positions in various contexts

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

    Names of people following titles or roles

    np_acts-logits-general · gemini-2.0-flash

    names following titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stalin
    -0.64
     CreateTagHelper
    -0.62
     Sarkozy
    -0.60
    Stalin
    -0.58
     Minaj
    -0.54
     Mbappe
    -0.51
     Odysseus
    -0.50
     Jehovah
    -0.50
     Buhari
    -0.50
     Gandhi
    -0.49
    POSITIVE LOGITS
     David
    0.87
     Mark
    0.85
     Michael
    0.84
     Mike
    0.84
    Mark
    0.83
     John
    0.83
     Chris
    0.79
    David
    0.78
    Mike
    0.75
    Michael
    0.75
    Act Density 1.695%

    No Known Activations