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

    Neuronpedia

    INDEX
    Explanations

    weights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    906
    -0.06
     enth
    -0.06
     औ
    -0.06
    addock
    -0.06
     gamma
    -0.06
     sett
    -0.06
    -supported
    -0.06
    圣
    -0.06
     Damon
    -0.06
    fa
    -0.06
    POSITIVE LOGITS
    section
    0.07
     복
    0.07
     Mul
    0.07
    .Im
    0.07
     infile
    0.06
    inery
    0.06
    نا
    0.06
    hibition
    0.06
    amble
    0.06
    pb
    0.06
    Act Density 0.133%

    No Known Activations