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

    Neuronpedia

    INDEX
    Explanations

    references to data structures and programming elements

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

    description strings in structured markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.68
     propOrder
    -0.67
     sumpay
    -0.64
    GEBURTS
    -0.60
    protoimpl
    -0.57
     gynhyrchwyd
    -0.57
    forChild
    -0.55
    genodigd
    -0.55
    AutoField
    -0.54
     Wicidata
    -0.51
    POSITIVE LOGITS
    TypeID
    0.35
     sound
    0.34
    IsSuccess
    0.33
    TypeCode
    0.33
     purpose
    0.33
     fact
    0.33
     razón
    0.32
     القص
    0.31
    лец
    0.31
     lyd
    0.31
    Act Density 0.038%

    No Known Activations