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

    Neuronpedia

    INDEX
    Explanations

    stay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stay
    -1.82
    stay
    -1.34
     remain
    -1.31
    Stay
    -1.24
     Stay
    -1.22
     stays
    -1.21
     STAY
    -1.13
    remain
    -1.13
     Remain
    -1.13
    STAY
    -1.03
    POSITIVE LOGITS
     Exactos
    0.68
     EconPapers
    0.64
    verwijspagina
    0.56
     LUMP
    0.54
    はじめに
    0.51
    godic
    0.50
     ExecuteAsync
    0.50
    Rujuakan
    0.50
    WebVitals
    0.49
    StoryboardSegue
    0.49
    Act Density 0.018%

    No Known Activations