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

    Neuronpedia

    INDEX
    Explanations

    parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     раздел
    -0.06
    ़ो
    -0.06
    _connection
    -0.06
     Mission
    -0.06
    汽车
    -0.06
    _gradient
    -0.06
    ativo
    -0.06
     Love
    -0.06
     fluffy
    -0.06
     gradient
    -0.06
    POSITIVE LOGITS
     parts
    0.09
    parts
    0.07
     وي
    0.06
    Article
    0.06
    170
    0.06
    pairs
    0.06
     |--------------------------------------------------------------------------↵
    0.06
     intf
    0.06
    intosh
    0.06
     James
    0.06
    Act Density 0.027%

    No Known Activations