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

    Neuronpedia

    INDEX
    Explanations

    work-life balance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Australia
    -0.08
    ((
    -0.08
     verwenden
    -0.08
    (CG
    -0.08
    (Binary
    -0.08
    (Qt
    -0.07
     cartilage
    -0.07
    (boost
    -0.07
    (
    -0.07
     Verwendung
    -0.07
    POSITIVE LOGITS
     interruptions
    0.12
     distractions
    0.11
    Interrupt
    0.11
     afternoons
    0.10
     errands
    0.10
     censor
    0.09
    _INTERRUPT
    0.09
     distracting
    0.09
     prioridades
    0.09
    interrupt
    0.09
    Act Density 0.076%

    No Known Activations