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

    Neuronpedia

    INDEX
    Explanations

    C variable types

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fd
    -0.07
    ativos
    -0.07
     process
    -0.06
     repeat
    -0.06
     sẽ
    -0.06
    政权
    -0.06
    绝
    -0.06
     essere
    -0.06
     concert
    -0.06
     пере
    -0.06
    POSITIVE LOGITS
     Happiness
    0.07
    oundingBox
    0.07
    до
    0.07
     Ingredients
    0.07
     Geli
    0.07
    {return
    0.07
    golden
    0.07
    𝑟
    0.07
     '',
↵
    0.07
    쩡
    0.07
    Act Density 0.023%

    No Known Activations