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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еи
    -0.07
    arcy
    -0.06
    恋
    -0.06
    (numbers
    -0.06
    (first
    -0.06
    (flags
    -0.06
    مه
    -0.06
     شدن
    -0.06
     pracovní
    -0.06
     phong
    -0.06
    POSITIVE LOGITS
    .Lines
    0.08
    classified
    0.07
    hit
    0.06
     indifferent
    0.06
    	describe
    0.06
     интер
    0.06
    (Have
    0.06
    _WARNINGS
    0.06
    _SW
    0.06
    ptype
    0.06
    Act Density 0.015%

    No Known Activations