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

    Neuronpedia

    INDEX
    Explanations

    throughput

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     květ
    -0.08
     지정
    -0.07
     proje
    -0.07
    datepicker
    -0.07
    ighest
    -0.06
    遣
    -0.06
     �
    -0.06
     vmin
    -0.06
    زینه
    -0.06
     сама
    -0.06
    POSITIVE LOGITS
     throughput
    0.16
    .We
    0.07
     Thankfully
    0.07
     comprehend
    0.06
    Beth
    0.06
     seeing
    0.06
    (IC
    0.06
     output
    0.06
     proprietor
    0.06
    (R
    0.06
    Act Density 0.001%

    No Known Activations