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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .inst
    -0.08
    ."↵↵↵
    -0.08
    קין
    -0.08
    ']↵↵↵
    -0.07
     )↵↵↵
    -0.07
    generated
    -0.07
    进行
    -0.07
    ))↵↵↵
    -0.07
    ())↵↵↵
    -0.07
     존재
    -0.07
    POSITIVE LOGITS
    �
    0.08
     propagation
    0.07
    ivityManager
    0.07
     disturbances
    0.07
     Bai
    0.07
    鲕
    0.07
    [Y
    0.07
    ôm
    0.07
     особенно
    0.07
    +i
    0.06
    Act Density 0.008%

    No Known Activations