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

    Neuronpedia

    INDEX
    Explanations

    numbers and death statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     showroom
    -0.09
     impedance
    -0.09
     buffers
    -0.08
     ambience
    -0.08
     perks
    -0.08
     knob
    -0.08
     sparkling
    -0.08
     pristine
    -0.08
     refreshments
    -0.08
     bandwidth
    -0.08
    POSITIVE LOGITS
     fatalities
    0.15
     deaths
    0.14
     victims
    0.12
     हत्या
    0.12
     হত্য
    0.12
     AIDS
    0.12
     perpetrators
    0.12
     homicide
    0.12
     मौत
    0.11
     मृत्यु
    0.11
    Act Density 0.058%

    No Known Activations