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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "left" and its variations in various contexts, indicating departures or exits

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

    leaving a place or position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RequiresApi
    -0.42
    XmlEnum
    -0.40
     AssemblyTitle
    -0.40
     препратки
    -0.40
    glTexCoord
    -0.40
    inum
    -0.39
     المعيارى
    -0.38
     itertools
    -0.38
    ModelSerializer
    -0.37
     CIL
    -0.36
    POSITIVE LOGITS
    Leaving
    0.80
     leaving
    0.80
     leave
    0.79
     Leaving
    0.77
    Leave
    0.75
     Leave
    0.75
    leaving
    0.69
     LEAVE
    0.68
    leave
    0.67
     quitté
    0.67
    Act Density 0.018%

    No Known Activations