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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Santo
    -0.08
    託
    -0.08
    фон
    -0.07
    :add
    -0.07
    (Connection
    -0.07
     imprisoned
    -0.07
    holder
    -0.07
     UNESCO
    -0.07
    _guard
    -0.07
    vers
    -0.07
    POSITIVE LOGITS
    בסופ
    0.08
    כרטיס
    0.07
     Ellie
    0.07
    文旅
    0.07
     callers
    0.07
    مسئول
    0.07
    _UI
    0.07
     accessibility
    0.07
    最美
    0.07
    無い
    0.07
    Act Density 0.012%

    No Known Activations