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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or entities within specific contexts

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

    Code, mathematics, and foreign language fragments

    np_acts-logits-general · gemini-2.0-flash

    sports, medical, programming context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     too
    -0.54
     to
    -0.50
     if
    -0.49
     المش
    -0.48
     as
    -0.48
     items
    -0.48
     a
    -0.47
     there
    -0.47
    1
    -0.47
    2
    -0.46
    POSITIVE LOGITS
     Efq
    1.12
     kasarigan
    1.03
    RegistryLite
    1.03
    SourceChecksum
    1.02
    Rüyada
    0.99
     estekak
    0.97
    帖最后由
    0.95
     Italijanski
    0.94
    InjectAttribute
    0.93
    asteroide
    0.91
    Act Density 0.309%

    No Known Activations