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

    Neuronpedia

    INDEX
    Explanations

    and/or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flour
    -0.07
    	test
    -0.06
     EQUAL
    -0.06
     Controls
    -0.06
    _Left
    -0.06
     nud
    -0.06
    _RED
    -0.06
    omatic
    -0.06
     #%
    -0.06
     adds
    -0.06
    POSITIVE LOGITS
    IDD
    0.08
    可能
    0.07
     зависимости
    0.07
     которого
    0.07
     gener
    0.07
    IGHL
    0.06
    td
    0.06
     ;
↵
↵
    0.06
    (IL
    0.06
     чим
    0.06
    Act Density 0.058%

    No Known Activations