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

    Neuronpedia

    INDEX
    Explanations

    references to unknown fields in data structures

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

    field number definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <
    -0.31
    <eos>
    -0.29
     Belgien
    -0.27
    ,
    -0.26
     extensa
    -0.25
     c
    -0.24
     habitudes
    -0.24
    -0.23
             
    -0.23
     ser
    -0.23
    POSITIVE LOGITS
    UnknownFieldSet
    1.28
    parsedMessage
    1.02
     unknownFields
    0.99
    BufferException
    0.97
    AccessorTable
    0.96
    CodedInputStream
    0.94
     queſto
    0.88
    <unused79>
    0.85
    <unused52>
    0.85
    [@BOS@]
    0.84
    Act Density 0.003%

    No Known Activations