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

    Neuronpedia

    INDEX
    Explanations

    Stop words and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Depos
    -0.06
     Rue
    -0.06
     lỗ
    -0.06
     kou
    -0.06
    (instruction
    -0.06
     Fern
    -0.06
     affili
    -0.06
     Island
    -0.06
     isVisible
    -0.06
    熊
    -0.06
    POSITIVE LOGITS
    Awesome
    0.07
     crafting
    0.07
    istory
    0.07
    오
    0.06
    Birthday
    0.06
    XXXXXXXX
    0.06
     seasoned
    0.06
    見
    0.06
    )↵↵↵↵
    0.06
     객체
    0.06
    Act Density 0.000%

    No Known Activations