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

    Neuronpedia

    INDEX
    Explanations

    MK

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    云南省
    -0.08
    UNK
    -0.07
     집
    -0.07
    BOOST
    -0.07
    שפה
    -0.07
    집
    -0.07
    요
    -0.07
    ="",
    -0.07
    zend
    -0.07
    复试
    -0.07
    POSITIVE LOGITS
     đọc
    0.07
     Rajasthan
    0.07
    .Rendering
    0.07
    篦
    0.06
    ⊗
    0.06
    👋
    0.06
     деят
    0.06
     Ritch
    0.06
     Phonetic
    0.06
    ráf
    0.06
    Act Density 0.000%

    No Known Activations