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

    Neuronpedia

    INDEX
    Explanations

    Chinese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     form
    -0.33
     mention
    -0.32
     out
    -0.32
     supply
    -0.30
    's
    -0.30
     mean
    -0.30
     similarity
    -0.30
     context
    -0.29
     (
    -0.29
     presence
    -0.29
    POSITIVE LOGITS
    çĭ¬ç«ĭ
    0.32
    èĥİ
    0.30
    èĩªçĦ¶
    0.29
    çĭ¬
    0.28
    ä¼ĺç§ĢçļĦ
    0.28
    ä¼ĺ
    0.28
    åĪ°æľĢåIJİ
    0.28
    æ´»åĬ¨
    0.28
    çļĦå¿ĥ
    0.28
    临æŶ
    0.27
    Act Density 0.091%

    No Known Activations