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

    Neuronpedia

    INDEX
    Explanations

    sum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    531
    -0.08
     nm
    -0.07
    density
    -0.07
    536
    -0.07
    136
    -0.07
     PURPOSE
    -0.07
    ्रपत
    -0.07
     比
    -0.07
     sterile
    -0.07
    肖
    -0.06
    POSITIVE LOGITS
    acağım
    0.07
    -dr
    0.06
     gzip
    0.06
    {
↵
    0.06
    ests
    0.06
     pest
    0.06
    $string
    0.06
     purge
    0.06
    ex
    0.06
     tag
    0.05
    Act Density 0.010%

    No Known Activations