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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ủ
    -0.07
    eným
    -0.07
    owel
    -0.06
     molt
    -0.06
     Hot
    -0.06
     thúc
    -0.06
    601
    -0.06
    _python
    -0.06
    >"
    -0.06
    ンデ
    -0.06
    POSITIVE LOGITS
    **↵
    0.06
    (character
    0.06
     downgrade
    0.06
    :string
    0.06
     宮
    0.06
    (Expression
    0.06
     ход
    0.06
    Servlet
    0.06
    uted
    0.06
     svn
    0.06
    Act Density 0.112%

    No Known Activations