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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    致富
    -0.07
    /sn
    -0.07
     קט
    -0.07
    度假
    -0.07
     автом
    -0.07
     хозя
    -0.07
    โม
    -0.06
     suç
    -0.06
    ︿
    -0.06
    经纪
    -0.06
    POSITIVE LOGITS
     Wikipedia
    0.07
    	HashMap
    0.06
    lixir
    0.06
    描述
    0.06
     sealed
    0.06
    無い
    0.06
    'https
    0.06
    	Scanner
    0.06
     Datensch
    0.06
     представлен
    0.06
    Act Density 0.001%

    No Known Activations