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

    Neuronpedia

    INDEX
    Explanations

    dominates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    анного
    -0.08
     कुनै
    -0.08
     புதிய
    -0.07
    }*/↵
    -0.07
    üğü
    -0.07
     Within
    -0.07
    }">↵
    -0.07
    些什么
    -0.07
     hansı
    -0.07
     lvl
    -0.07
    POSITIVE LOGITS
     dominates
    0.16
     dominate
    0.14
     dominating
    0.14
     dominance
    0.14
     predomin
    0.14
     dominante
    0.13
    domin
    0.13
     dominant
    0.13
     많
    0.12
     domina
    0.12
    Act Density 0.024%

    No Known Activations