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

    Neuronpedia

    INDEX
    Explanations

    human statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    她
    -0.07
    他们
    -0.07
     IllegalStateException
    -0.06
     gradually
    -0.06
    objs
    -0.06
    Transformer
    -0.06
    Color
    -0.06
     reading
    -0.06
     Sales
    -0.06
     Current
    -0.06
    POSITIVE LOGITS
    лександ
    0.07
    ские
    0.06
     플레이
    0.06
     matcher
    0.06
    "]/
    0.06
     мої
    0.06
    irmware
    0.06
     (>
    0.06
    ertext
    0.06
     рань
    0.06
    Act Density 0.024%

    No Known Activations