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

    Neuronpedia

    INDEX
    Explanations

    棒

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     starring
    -0.08
     Wellness
    -0.08
    ละคร
    -0.08
    Hollywood
    -0.07
    _FUN
    -0.07
    住宿
    -0.07
     Gover
    -0.07
    _house
    -0.07
    ाहित
    -0.07
     بالط
    -0.07
    POSITIVE LOGITS
     robustness
    0.15
     Robust
    0.13
     resilient
    0.12
     insensitive
    0.12
     robust
    0.12
     gegenüber
    0.11
     resilience
    0.11
     withstand
    0.11
    against
    0.11
     against
    0.11
    Act Density 0.019%

    No Known Activations