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

    Neuronpedia

    INDEX
    Explanations

    correctness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.28
    ypress
    -0.28
    azer
    -0.27
    iaz
    -0.27
    éĵį
    -0.27
    abb
    -0.25
    osal
    -0.24
     '"+
    -0.24
    fx
    -0.24
     tentative
    -0.24
    POSITIVE LOGITS
    æĤĶ
    0.29
    obi
    0.27
     dur
    0.25
    对èĩªå·±
    0.24
     cocci
    0.24
     spreads
    0.24
     counted
    0.23
     Indices
    0.23
    çħİ
    0.23
    弯
    0.23
    Act Density 0.063%

    No Known Activations