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

    Neuronpedia

    INDEX
    Explanations

    code segments related to Android support libraries

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

    begin of turn markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.88
    RegressionTest
    -0.84
    parsedMessage
    -0.80
    awtextra
    -0.77
    GenerationType
    -0.77
    ViewImports
    -0.73
     BoxFit
    -0.72
    SharedDtor
    -0.72
     Geiſt
    -0.72
     ſei
    -0.71
    POSITIVE LOGITS
    .
    0.57
     
    0.53
     basic
    0.51
     the
    0.47
    ,
    0.47
     a
    0.46
     an
    0.46
     few
    0.46
    {
    0.45
     (
    0.44
    Act Density 0.011%

    No Known Activations