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

    Neuronpedia

    INDEX
    Explanations

    uncontrollable events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oldu
    -0.08
    orsche
    -0.08
     testimonials
    -0.08
     cashback
    -0.08
     backpack
    -0.08
     reassurance
    -0.08
     payoff
    -0.08
     mileage
    -0.07
    ahre
    -0.07
     Coach
    -0.07
    POSITIVE LOGITS
     afflicted
    0.10
    Affected
    0.09
     disturbances
    0.09
     disturbed
    0.09
    affected
    0.09
    战争
    0.08
     raisonn
    0.08
     unpredict
    0.08
    Interrupted
    0.08
     unfore
    0.08
    Act Density 0.003%

    No Known Activations