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

    Neuronpedia

    INDEX
    Explanations

    numbers and their associations with quantities and values

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

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.66
     endblock
    -0.62
     AssemblyCulture
    -0.62
     ProtoMessage
    -0.57
     özellikle
    -0.53
     Forderung
    -0.52
    SharedDtor
    -0.51
    ceria
    -0.50
     cereales
    -0.50
     sowas
    -0.49
    POSITIVE LOGITS
     six
    0.59
     seven
    0.56
     three
    0.56
     eight
    0.55
     nine
    0.53
     four
    0.53
     ſeveral
    0.51
     additional
    0.49
     five
    0.49
     two
    0.48
    Act Density 0.262%

    No Known Activations