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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TREE
    -0.07
    Direccion
    -0.07
    _mean
    -0.06
     UR
    -0.06
     perfect
    -0.06
     eius
    -0.06
    яз
    -0.06
     languages
    -0.06
    告
    -0.06
    _IN
    -0.06
    POSITIVE LOGITS
    idence
    0.07
     S
    0.07
    _property
    0.06
    inston
    0.06
    ale
    0.06
     Instantiate
    0.06
    تب
    0.06
    xab
    0.06
     Axios
    0.06
    ừng
    0.06
    Act Density 0.030%

    No Known Activations