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

    Neuronpedia

    INDEX
    Explanations

    the Guardian newspaper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     differentiating
    0.46
    临床
    0.40
     Pune
    0.40
    饵
    0.40
    َر
    0.39
     DER
    0.39
    Pune
    0.39
    odeling
    0.39
     differentiation
    0.39
    鉻
    0.39
    POSITIVE LOGITS
     Guardian
    1.16
    Guardian
    1.13
    guardian
    1.04
     guardian
    0.98
     guardians
    0.87
     Guardians
    0.85
    guard
    0.72
    Guard
    0.70
     গার্ডিয়ান
    0.68
     गार्ड
    0.68
    Act Density 0.001%

    No Known Activations