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

    Neuronpedia

    INDEX
    Explanations

    continue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uş
    -0.07
     tv
    -0.07
     infiltr
    -0.07
    (OP
    -0.07
    уки
    -0.07
    ůvod
    -0.07
    чів
    -0.06
     rebound
    -0.06
    <span
    -0.06
    `
    -0.06
    POSITIVE LOGITS
     remains
    0.07
     GRAT
    0.06
     Jerseys
    0.06
     Thunder
    0.06
    antage
    0.06
     Pharmacy
    0.06
    .sd
    0.06
    ")}
    0.06
     ฝ
    0.06
    ylation
    0.06
    Act Density 0.026%

    No Known Activations