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

    Neuronpedia

    INDEX
    Explanations

    loopback addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (anchor
    -0.07
     Михай
    -0.07
     Hibernate
    -0.07
     multin
    -0.07
    捕
    -0.06
    })();↵
    -0.06
    atak
    -0.06
    .Text
    -0.06
     newSize
    -0.06
    ">
↵
↵
    -0.06
    POSITIVE LOGITS
    .flush
    0.07
    Benchmark
    0.06
    =df
    0.06
    .filtered
    0.06
     forex
    0.06
     خورد
    0.06
    537
    0.06
     kick
    0.06
     fucking
    0.06
    ў
    0.06
    Act Density 0.009%

    No Known Activations