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

    Neuronpedia

    INDEX
    Explanations

    ensemble

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teplot
    -0.07
     capitalism
    -0.07
    }:
    -0.06
    >Date
    -0.06
    าท
    -0.06
     popped
    -0.06
    Warn
    -0.06
    Argentina
    -0.06
     imperialism
    -0.06
     香港
    -0.06
    POSITIVE LOGITS
     ensemble
    0.14
     Ensemble
    0.12
     ensued
    0.09
    Inset
    0.07
    ensemble
    0.07
    نان
    0.07
    naments
    0.07
    sembles
    0.07
    ensem
    0.07
    Ан
    0.06
    Act Density 0.002%

    No Known Activations