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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Frames
    -0.08
     子
    -0.08
     одна
    -0.07
    單
    -0.07
     встанов
    -0.07
    样子
    -0.07
    /her
    -0.07
     ebony
    -0.06
     レ
    -0.06
    Sell
    -0.06
    POSITIVE LOGITS
    ))?
    0.07
    %)↵↵
    0.06
    ptides
    0.06
    <Map
    0.06
    Concrete
    0.06
     bitk
    0.06
    want
    0.06
     narrower
    0.06
     Arrest
    0.06
    )|(
    0.06
    Act Density 0.000%

    No Known Activations