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

    Neuronpedia

    INDEX
    Explanations

    Stopping/pausing code processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Є
    -0.09
     चरण
    -0.08
     uniques
    -0.08
    step
    -0.08
     beneficial
    -0.07
    Unique
    -0.07
    SEM
    -0.07
    -0.07
    _unique
    -0.07
     단계
    -0.07
    POSITIVE LOGITS
    停止
    0.13
     Interrupt
    0.12
     interruptions
    0.12
    Interrupt
    0.12
     прекращ
    0.12
     interruption
    0.12
    _interrupt
    0.12
    取消
    0.12
    	stop
    0.11
     STOP
    0.11
    Act Density 0.006%
    No Known Activations