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

    Neuronpedia

    INDEX
    Explanations

    references to versioning and identifiers related to software or documents

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

    code structures and versioning information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.84
    IsMutable
    -0.84
     erſt
    -0.83
     queſta
    -0.82
     ſeine
    -0.81
     beſte
    -0.81
    ſchaft
    -0.80
     erſten
    -0.80
     ſei
    -0.80
     ſeiner
    -0.80
    POSITIVE LOGITS
     etc
    0.36
     and
    0.30
     TAMBIÉN
    0.30
    ,
    0.30
     Evangelio
    0.28
    .
    0.28
     gibi
    0.28
     tranquila
    0.27
     brisa
    0.27
     tranquilo
    0.27
    Act Density 0.019%

    No Known Activations