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

    Neuronpedia

    INDEX
    Explanations

    .T

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    пло
    -0.31
    ythe
    -0.29
     Vere
    -0.28
     пло
    -0.28
    поÑĩ
    -0.28
     ))↵
    -0.28
    plate
    -0.27
     dee
    -0.27
    ä¸įèī¯
    -0.27
     plate
    -0.26
    POSITIVE LOGITS
    ä»Ĺ
    0.30
    -density
    0.27
    oes
    0.27
    rown
    0.27
    ont
    0.26
    ukt
    0.25
    ardon
    0.25
    æ´²
    0.25
    %</
    0.25
    å¯Ĩ度
    0.25
    Act Density 0.044%

    No Known Activations