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

    Neuronpedia

    INDEX
    Explanations

    controversial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     automáticamente
    -0.07
    AUSE
    -0.07
    -module
    -0.07
    (kwargs
    -0.06
    rx
    -0.06
    סד
    -0.06
    UV
    -0.06
    -my
    -0.06
     gratuitement
    -0.06
    各行各业
    -0.06
    POSITIVE LOGITS
    ゞ
    0.07
     odio
    0.07
     Nathan
    0.07
    ◢
    0.07
     README
    0.07
    意見
    0.07
    =$_
    0.07
    0.07
    지를
    0.06
    ♣
    0.06
    Act Density 0.106%

    No Known Activations