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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bur
    -0.07
    SqlServer
    -0.06
     fans
    -0.06
    p
    -0.06
     disadvantaged
    -0.06
     Gar
    -0.06
    -0.06
    workers
    -0.06
     podí
    -0.06
     Golf
    -0.06
    POSITIVE LOGITS
     symbolism
    0.08
    UNCH
    0.07
     cez
    0.07
    ARGV
    0.07
    IXEL
    0.06
     parameter
    0.06
     hopping
    0.06
     노하우
    0.06
     concurrency
    0.06
    _ETH
    0.06
    Act Density 0.017%

    No Known Activations