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

    Neuronpedia

    INDEX
    Explanations

    phrases related to staying connected digitally or personally

    oai_token-act-pair · gemini-2.0-flash

    staying in contact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.73
    RegressionTest
    -0.63
    writeFieldEnd
    -0.58
    nto
    -0.58
    Personensuche
    -0.57
     ExecuteAsync
    -0.55
     dele
    -0.53
    JsonHelper
    -0.52
    LookAnd
    -0.52
     Gae
    -0.52
    POSITIVE LOGITS
     stays
    0.86
     Stay
    0.84
     stay
    0.82
     Keep
    0.81
     maintains
    0.75
     Keeping
    0.75
     stayed
    0.73
     keep
    0.73
    Stay
    0.73
    keep
    0.72
    Act Density 0.718%

    No Known Activations