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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BaseController
    -0.06
    Operations
    -0.06
    수를
    -0.06
    쓰
    -0.06
    处理
    -0.06
     chinese
    -0.06
     '&'
    -0.06
     NoSuch
    -0.06
     CHANNEL
    -0.06
    urile
    -0.06
    POSITIVE LOGITS
    μπο
    0.07
    Ha
    0.07
     Sunshine
    0.06
    Most
    0.06
    acted
    0.06
     куб
    0.06
     Lions
    0.06
     وی
    0.06
    يمكن
    0.06
     Laos
    0.06
    Act Density 0.037%

    No Known Activations