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

    Neuronpedia

    INDEX
    Explanations

    exit or quit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    শ্রেষ্ঠ
    0.47
    nelly
    0.40
    ancha
    0.40
    bumptech
    0.40
    選び
    0.39
    IndexPath
    0.39
     licking
    0.39
    architect
    0.38
    アルバ
    0.38
    aksanaan
    0.37
    POSITIVE LOGITS
    退出
    0.61
     Exit
    0.61
     quit
    0.60
    Quit
    0.60
     exit
    0.59
     Quit
    0.56
     Termination
    0.56
    Exit
    0.55
    终止
    0.55
    EOF
    0.55
    Act Density 0.082%

    No Known Activations