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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    澴
    -0.08
    (byte
    -0.08
    Activities
    -0.07
    successfully
    -0.07
    衷心
    -0.07
     proceedings
    -0.07
     sentenced
    -0.07
    książ
    -0.07
     Representatives
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    基金管理
    0.07
    กระจ
    0.07
    \Foundation
    0.07
     cigar
    0.07
     reclaim
    0.06
     Starter
    0.06
    减免
    0.06
    _GRP
    0.06
    厭
    0.06
     Society
    0.06
    Act Density 0.127%

    No Known Activations