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

    Neuronpedia

    INDEX
    Explanations

    beard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UIKit
    -0.07
    head
    -0.07
    거나
    -0.06
     Versions
    -0.06
    408
    -0.06
     т
    -0.06
    992
    -0.06
    (news
    -0.06
     Often
    -0.06
     Actor
    -0.06
    POSITIVE LOGITS
    #w
    0.06
    )",
    0.06
    .Commands
    0.06
    }',
    0.06
     quand
    0.05
     asign
    0.05
     vive
    0.05
     立
    0.05
    Eine
    0.05
     평
    0.05
    Act Density 0.009%

    No Known Activations