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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    antha
    -0.08
    holes
    -0.07
     Ethics
    -0.06
     Cooke
    -0.06
    邊
    -0.06
    riott
    -0.06
    iou
    -0.06
    ้นท
    -0.06
    택
    -0.06
    тия
    -0.06
    POSITIVE LOGITS
     basically
    0.07
    .addRow
    0.07
    .attr
    0.07
    ับร
    0.06
     lending
    0.06
     وغير
    0.06
    (encoding
    0.06
     yarn
    0.06
     например
    0.06
    /UIKit
    0.06
    Act Density 0.592%

    No Known Activations