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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to non-trivial mathematical properties and structures

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

    non-trivial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tại
    -0.34
    Hyde
    -0.32
    小
    -0.30
    __
    -0.29
     flat
    -0.29
     entirely
    -0.28
    的小
    -0.28
    DropColumn
    -0.28
    Down
    -0.28
    kan
    -0.28
    POSITIVE LOGITS
    Diweddarwch
    0.68
    isNotEmpty
    0.68
    protoimpl
    0.68
     للاسماء
    0.67
     nonzero
    0.66
     فريبيس
    0.64
    NotNil
    0.61
    GTCX
    0.60
    Rohy
    0.60
     nontrivial
    0.59
    Act Density 0.398%

    No Known Activations