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

    Neuronpedia

    INDEX
    Explanations

    Brit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    贸
    -0.08
    owie
    -0.08
    魈
    -0.08
    ponder
    -0.07
    onymous
    -0.07
     wsp
    -0.07
    EOS
    -0.07
    ToDevice
    -0.07
     true
    -0.07
    adero
    -0.07
    POSITIVE LOGITS
     Brit
    0.09
    Brit
    0.09
    Pat
    0.07
     wrześ
    0.07
    (lat
    0.07
     pirate
    0.07
    "](
    0.07
    га
    0.07
     _↵↵
    0.07
     denim
    0.07
    Act Density 0.003%

    No Known Activations