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

    Neuronpedia

    INDEX
    Explanations

    has not been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prefs
    -0.07
     collectively
    -0.06
    리아
    -0.06
    ैक
    -0.06
    	size
    -0.06
    ffc
    -0.06
     ře
    -0.06
    ičky
    -0.06
     vůbec
    -0.06
    за
    -0.06
    POSITIVE LOGITS
    》↵
    0.07
     Wilmington
    0.07
     setType
    0.07
     Christopher
    0.06
    fresh
    0.06
    年的
    0.06
     embroidery
    0.06
    DH
    0.06
     яких
    0.06
     vlád
    0.06
    Act Density 0.002%

    No Known Activations