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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce lists or resources

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

    after "here are" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    lists of numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.75
    SequentialGroup
    -0.70
    Geplaatst
    -0.69
    Искәрмәләр
    -0.67
    存于互联网档案馆
    -0.65
     שוליים
    -0.63
     صوتيه
    -0.61
     CreateTagHelper
    -0.61
    setVerticalGroup
    -0.58
     Roskov
    -0.56
    POSITIVE LOGITS
     five
    1.25
     Top
    1.17
    Top
    1.09
     seven
    1.07
     top
    1.02
     six
    0.99
     ten
    0.99
     Five
    0.98
     cinco
    0.98
    five
    0.97
    Act Density 0.116%

    No Known Activations