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

    Neuronpedia

    INDEX
    Explanations

    taxes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     livro
    -0.07
     []*
    -0.07
    Alice
    -0.06
    立刻
    -0.06
    like
    -0.06
    uh
    -0.06
    ，
    -0.06
    áč
    -0.06
    Mad
    -0.06
     Edward
    -0.06
    POSITIVE LOGITS
    _POSITION
    0.06
     outr
    0.06
    '/>↵
    0.06
    <Select
    0.06
    	Add
    0.06
     говор
    0.06
     realize
    0.06
     shaping
    0.06
    .getLength
    0.06
     نظام
    0.06
    Act Density 0.012%

    No Known Activations