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

    Neuronpedia

    INDEX
    Explanations

    exiting programs / code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tring
    -0.09
     stocking
    -0.08
     roofs
    -0.08
     subscription
    -0.08
    nibus
    -0.08
     empowerment
    -0.08
     capacit
    -0.08
     backbone
    -0.08
     underserved
    -0.08
     Empower
    -0.08
    POSITIVE LOGITS
    退出
    0.15
    (EXIT
    0.13
    EXIT
    0.12
    .exit
    0.12
    .Exit
    0.12
    (exit
    0.12
    終了
    0.12
     EXIT
    0.12
     종료
    0.11
    死亡
    0.11
    Act Density 0.005%

    No Known Activations