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

    Neuronpedia

    INDEX
    Explanations

    leaving and quitting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aik
    0.75
     リュ
    0.72
    Ambient
    0.71
    modifier
    0.70
     restored
    0.70
    körper
    0.69
     compresses
    0.69
    霖
    0.68
    Annotations
    0.68
    滤
    0.67
    POSITIVE LOGITS
     quitting
    2.58
     leaving
    2.52
     exit
    2.51
     departure
    2.42
     departing
    2.36
     Exit
    2.34
    exit
    2.32
     quit
    2.30
     Leaving
    2.28
     quitter
    2.25
    Act Density 0.184%

    No Known Activations