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

    Neuronpedia

    INDEX
    Explanations

    rules of conduct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     கை
    -0.08
    _parallel
    -0.07
    /static
    -0.07
    /grid
    -0.07
     spenn
    -0.07
    weep
    -0.07
     固
    -0.07
     overwritten
    -0.07
    /details
    -0.07
     Sentinel
    -0.07
    POSITIVE LOGITS
     courteous
    0.17
     respectful
    0.17
     احترام
    0.14
     respeto
    0.13
    尊
    0.13
     уваж
    0.12
     courte
    0.12
     considerate
    0.12
     upheld
    0.12
     соблюдать
    0.12
    Act Density 0.057%

    No Known Activations